One read of Claude Documentationclaude-docs-20260928T220706Z
157 pages moved out of 255 read.
Pages moved
157
significant first
Pages read
255
in this capture
Captured
22:07 UTC
Corpus hash
9aad7bf66b91
corpus-hash
What this read moved
1-25 of 157, page 1 of 7This capture is too large to show at once. Changes 1-25 of 157 are below, significant first; the rest are on the following screens.
claude-science/admin-controls Changed · +63 / -63 lines
from line 12
1212
1313Each control starts at a default that depends on your plan and on whether HIPAA compliance is enabled for your organization. The page always shows the value in force for your organization.
1414
15| Control | Default for Team | Default for Enterprise¹ |
16| ------------------------------------------------------------------------------ | ------------------------------ | ------------------------------ |
17| Featured connectors and Featured skills | All on | All on |
18| Allow custom connectors | On | Off |
19| Allow custom skills | On | On |
20| Allow members to access Claude Science work previously saved on their computer | On | Off |
21| Manage network allowlist | Off (members manage their own) | Off (members manage their own) |
22| Organization package mirror | Not set | Not set |
23| Allow members to connect SSH hosts | On | On |
24| Allow members to connect to Modal | On | Off |
25| Show scientific model endpoint providers on the Compute tab | On | On |
26| Turn on memory for your team | On | On |
15| Control | Default for Team | Default for Enterprise¹ |
16| - | - | - |
17| Featured connectors and Featured skills | All on | All on |
18| Allow custom connectors | On | Off |
19| Allow custom skills | On | On |
20| Allow members to access Claude Science work previously saved on their computer | On | Off |
21| Manage network allowlist | Off (members manage their own) | Off (members manage their own) |
22| Organization package mirror | Not set | Not set |
23| Allow members to connect SSH hosts | On | On |
24| Allow members to connect to Modal | On | Off |
25| Show scientific model endpoint providers on the Compute tab | On | On |
26| Turn on memory for your team | On | On |
2727
2828¹ For HIPAA-eligible organizations, note that Claude Science (beta) is not covered under your Business Associate Agreement (BAA) and should not be used with protected health information (PHI). Administrators who enable Claude Science are responsible for ensuring their workforce uses it in compliance with applicable legal obligations. Featured and custom connectors, SSH hosts, Modal, scientific model endpoints, memory, and access to previously saved Claude Science work are all off by default for HIPAA-eligible organizations.
2929
from line 182
182182
183183### Identity and access
184184
185| Setting in claude.ai | Status for Claude Science | Note |
186| ----------------------------------------------------------------------------- | ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
187| Organization and access > Single sign-on (SSO) | Supported in Claude Science | Members sign in to Claude Science through claude.ai, so your SSO configuration and the **Require SSO for Claude** setting apply to the app. |
188| Organization and access > User provisioning (SCIM directory sync, Enterprise) | Supported in Claude Science | Provisioning and deprovisioning act on claude.ai membership, which Anthropic checks on every request the app makes, so a deprovisioned member's app stops working. |
189| Organization and access > Domains | Supported in Claude Science | Domain verification, and the **Migrate accounts using your domains** and **Restrict organization creation** settings that build on it, act on claude.ai accounts before anyone reaches the app, so they apply unchanged. |
190| Members | Supported in Claude Science | Adding or removing members controls who can sign in to Claude Science. |
191| Roles (built-in) | Supported in Claude Science | Every built-in role (User, Admin, Owner, and Primary Owner) can use Claude Science once it's turned on for the organization. |
192| Roles > Claude Science permission in custom roles (Enterprise) | Supported in Claude Science | Add the Claude Science permission to a custom role to give the app to that role's members. Members whose custom roles don't include it can't use the app. Team plans don't have custom roles, so everyone gets access when Claude Science is on. |
193| Groups (Enterprise) | Supported in Claude Science | Members get the Claude Science access of the roles their groups assign. |
194| IP allowlist (Enterprise) | Partially supported in Claude Science | The app's sign-in, its requests to Claude, and its Directory connector calls are checked against your allowlist (see [Restrict access to Claude with IP allowlisting](https://support.claude.com/en/articles/13200993-restrict-access-to-claude-with-ip-allowlisting)). Traffic that doesn't go to Anthropic isn't checked, which covers code on the member's computer, SSH hosts, or Modal account, and custom connectors members add in the app. You can turn SSH hosts, Modal, and custom connectors off under [Organization settings](#organization-settings). |
195| Organization and access > Shortened session length (Enterprise) | Partially supported in Claude Science | Applies to the browser sign-in a member completes to connect the app. It doesn't shorten the app's own sign-in after that, so members aren't asked to sign in again on your schedule. Turning Claude Science off for the organization or removing a member still stops their app within a few minutes. |
185| Setting in claude.ai | Status for Claude Science | Note |
186| - | - | - |
187| Organization and access > Single sign-on (SSO) | Supported in Claude Science | Members sign in to Claude Science through claude.ai, so your SSO configuration and the **Require SSO for Claude** setting apply to the app. |
188| Organization and access > User provisioning (SCIM directory sync, Enterprise) | Supported in Claude Science | Provisioning and deprovisioning act on claude.ai membership, which Anthropic checks on every request the app makes, so a deprovisioned member's app stops working. |
189| Organization and access > Domains | Supported in Claude Science | Domain verification, and the **Migrate accounts using your domains** and **Restrict organization creation** settings that build on it, act on claude.ai accounts before anyone reaches the app, so they apply unchanged. |
190| Members | Supported in Claude Science | Adding or removing members controls who can sign in to Claude Science. |
191| Roles (built-in) | Supported in Claude Science | Every built-in role (User, Admin, Owner, and Primary Owner) can use Claude Science once it's turned on for the organization. |
192| Roles > Claude Science permission in custom roles (Enterprise) | Supported in Claude Science | Add the Claude Science permission to a custom role to give the app to that role's members. Members whose custom roles don't include it can't use the app. Team plans don't have custom roles, so everyone gets access when Claude Science is on. |
193| Groups (Enterprise) | Supported in Claude Science | Members get the Claude Science access of the roles their groups assign. |
194| IP allowlist (Enterprise) | Partially supported in Claude Science | The app's sign-in, its requests to Claude, and its Directory connector calls are checked against your allowlist (see [Restrict access to Claude with IP allowlisting](https://support.claude.com/en/articles/13200993-restrict-access-to-claude-with-ip-allowlisting)). Traffic that doesn't go to Anthropic isn't checked, which covers code on the member's computer, SSH hosts, or Modal account, and custom connectors members add in the app. You can turn SSH hosts, Modal, and custom connectors off under [Organization settings](#organization-settings). |
195| Organization and access > Shortened session length (Enterprise) | Partially supported in Claude Science | Applies to the browser sign-in a member completes to connect the app. It doesn't shorten the app's own sign-in after that, so members aren't asked to sign in again on your schedule. Turning Claude Science off for the organization or removing a member still stops their app within a few minutes. |
196196
197197### Capability toggles
198198
199| Setting in claude.ai | Status for Claude Science | Note |
200| -------------------------------------------------------------------------------- | -------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
201| Claude Science > Enable for your organization | Supported in Claude Science | Off by default for Team and Enterprise. An Owner or Primary Owner turns it on under **Organization settings** > **Claude Science** (see [Enable Claude Science](/docs/claude-science/enable-claude-science)). Assigning seats doesn't turn it on. |
202| Data and privacy > Rate chats | Supported in Claude Science | When you turn this off, the app hides its response rating buttons and feedback form, as claude.ai does. If your organization uses customer-managed encryption keys (CMEK), you can't turn this setting on and the app doesn't show these controls. |
203| Organization and access > Organization instructions | Supported in Claude Science | Anthropic adds your organization instructions to the app's requests to Claude, as it does for claude.ai chat, so members don't need to update the app for a change to apply. |
204| Skills > Organization skills and Policy | Supported in Claude Science | Skills you add under **Organization skills**, and members' own claude.ai skills, appear in Claude Science while **Skills** is on, and **User-created skills** decides whether a member can save a skill from the app to their own claude.ai account. The skills that come with the app and the skills members add in it are controlled on the **Claude Science** page: one switch per Featured skill, and **Allow custom skills** for skills members add themselves (see [Featured connectors and skills](#featured-connectors-and-skills) and [Custom skills](#custom-skills)). |
205| Capabilities > Web search | Not applicable in Claude Science | This setting governs claude.ai chat. Claude Science can search the web regardless of it, and the **Claude Science** page has no switch for web search. |
206| Capabilities > Code execution and file creation | Not applicable in Claude Science | This setting governs the code sandbox Anthropic hosts for claude.ai chat. Running code on the member's computer, or on compute the member connects, is the core of Claude Science and can't be turned off; you govern what that code can reach with the [network allowlist](#network-allowlist), [SSH hosts](#ssh-hosts), and [Modal](#modal) controls. |
207| Capabilities > Allow network egress and Domain allowlist | Supported in Claude Science | These settings govern the hosted sandbox for claude.ai chat. Claude Science's sandbox has its own allowlist: manage it for the whole organization with the **Manage network allowlist** switch on the **Claude Science** page (see [Network allowlist](#network-allowlist)), or leave it off and let members manage their own. Administrators can also extend a member's list per device with the sandbox network keys in the [configuration file reference](/docs/claude-science/configuration-file-reference). |
208| Data and privacy > Location metadata | Not applicable in Claude Science | Claude Science doesn't send location data with requests to Claude, so there is nothing for this setting to govern. |
209| Capabilities > Memory (Enable memory for your team) | Supported in Claude Science | This setting governs memory in claude.ai chat. Claude Science keeps a separate memory on each member's computer, which you turn on or off for everyone with the **Turn on memory for your team** switch on the **Claude Science** page (see [Memory](#memory)). |
210| Settings for claude.ai projects (Public projects, Retention period for projects) | Not applicable in Claude Science | Claude Science doesn't use claude.ai projects. Its projects are folders on the member's computer. |
199| Setting in claude.ai | Status for Claude Science | Note |
200| - | - | - |
201| Claude Science > Enable for your organization | Supported in Claude Science | Off by default for Team and Enterprise. An Owner or Primary Owner turns it on under **Organization settings** > **Claude Science** (see [Enable Claude Science](/docs/claude-science/enable-claude-science)). Assigning seats doesn't turn it on. |
202| Data and privacy > Rate chats | Supported in Claude Science | When you turn this off, the app hides its response rating buttons and feedback form, as claude.ai does. If your organization uses customer-managed encryption keys (CMEK), you can't turn this setting on and the app doesn't show these controls. |
203| Organization and access > Organization instructions | Supported in Claude Science | Anthropic adds your organization instructions to the app's requests to Claude, as it does for claude.ai chat, so members don't need to update the app for a change to apply. |
204| Skills > Organization skills and Policy | Supported in Claude Science | Skills you add under **Organization skills**, and members' own claude.ai skills, appear in Claude Science while **Skills** is on, and **User-created skills** decides whether a member can save a skill from the app to their own claude.ai account. The skills that come with the app and the skills members add in it are controlled on the **Claude Science** page: one switch per Featured skill, and **Allow custom skills** for skills members add themselves (see [Featured connectors and skills](#featured-connectors-and-skills) and [Custom skills](#custom-skills)). |
205| Capabilities > Web search | Not applicable in Claude Science | This setting governs claude.ai chat. Claude Science can search the web regardless of it, and the **Claude Science** page has no switch for web search. |
206| Capabilities > Code execution and file creation | Not applicable in Claude Science | This setting governs the code sandbox Anthropic hosts for claude.ai chat. Running code on the member's computer, or on compute the member connects, is the core of Claude Science and can't be turned off; you govern what that code can reach with the [network allowlist](#network-allowlist), [SSH hosts](#ssh-hosts), and [Modal](#modal) controls. |
207| Capabilities > Allow network egress and Domain allowlist | Supported in Claude Science | These settings govern the hosted sandbox for claude.ai chat. Claude Science's sandbox has its own allowlist: manage it for the whole organization with the **Manage network allowlist** switch on the **Claude Science** page (see [Network allowlist](#network-allowlist)), or leave it off and let members manage their own. Administrators can also extend a member's list per device with the sandbox network keys in the [configuration file reference](/docs/claude-science/configuration-file-reference). |
208| Data and privacy > Location metadata | Not applicable in Claude Science | Claude Science doesn't send location data with requests to Claude, so there is nothing for this setting to govern. |
209| Capabilities > Memory (Enable memory for your team) | Supported in Claude Science | This setting governs memory in claude.ai chat. Claude Science keeps a separate memory on each member's computer, which you turn on or off for everyone with the **Turn on memory for your team** switch on the **Claude Science** page (see [Memory](#memory)). |
210| Settings for claude.ai projects (Public projects, Retention period for projects) | Not applicable in Claude Science | Claude Science doesn't use claude.ai projects. Its projects are folders on the member's computer. |
211211
212212### Connectors
213213
214| Setting in claude.ai | Status for Claude Science | Note |
215| ---------------------------------------------------------- | ------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
216| Connectors > connectors you add for your organization | Supported in Claude Science | Connectors you add on the **Connectors** page, from the directory or by web address (custom connectors), are available to members in the app, as in claude.ai. Claude connects to them from Anthropic's servers, and members sign in with their own accounts where needed. |
217| Roles > connector permissions in custom roles (Enterprise) | Partially supported in Claude Science | Apply to the connectors on your **Connectors** page, which the app reaches through Anthropic. They don't apply to Featured connectors or custom connectors added via the Claude Science app; the **Claude Science** page controls those for every member rather than per role (see [Organization settings](#organization-settings)). |
218| Plugins > plugins you add for the organization | Partially supported in Claude Science | Plugins you set to **Installed by default** or **Required** are synced to members' Claude Science app, which loads their skills and connectors. Plugins left as **Available to install** aren't offered in the app, and plugin commands don't apply there. Which Featured connectors and skills members can use, and whether they can add their own, are separate controls on the **Claude Science** page (see [Featured connectors and skills](#featured-connectors-and-skills), [Custom connectors](#custom-connectors), and [Custom skills](#custom-skills)). |
219| Connectors > Tunnels API (Enterprise) | Partially supported in Claude Science | A connector your organization serves through a tunnel works in the app the same way it does in claude.ai, because the app reaches the connectors on your **Connectors** page through Anthropic's hosted connector service. Custom connectors a member adds in the Claude Science app connect directly from the member's computer and never use a tunnel (admins can restrict this in [Custom connectors](#custom-connectors)). |
220| Connectors > connectors members add themselves | Supported in Claude Science | In claude.ai, members use only the connectors on your **Connectors** page. In Claude Science, members can also add custom connectors (a server URL or a local command) while the **Allow custom connectors** switch is on, which it is by default for Team and not for Enterprise, and the **Connectors** page and its restrictions don't apply to those. Turn off the **Allow custom connectors** switch under **Organization settings** > **Claude Science** to limit members to Featured connectors and the connectors you add on your **Connectors** page (see [Custom connectors](#custom-connectors)). |
221| Connectors > Desktop extension allowlist | Not applicable in Claude Science | Claude Science doesn't install desktop extensions, so there is nothing for this setting to govern. |
214| Setting in claude.ai | Status for Claude Science | Note |
215| - | - | - |
216| Connectors > connectors you add for your organization | Supported in Claude Science | Connectors you add on the **Connectors** page, from the directory or by web address (custom connectors), are available to members in the app, as in claude.ai. Claude connects to them from Anthropic's servers, and members sign in with their own accounts where needed. |
217| Roles > connector permissions in custom roles (Enterprise) | Partially supported in Claude Science | Apply to the connectors on your **Connectors** page, which the app reaches through Anthropic. They don't apply to Featured connectors or custom connectors added via the Claude Science app; the **Claude Science** page controls those for every member rather than per role (see [Organization settings](#organization-settings)). |
218| Plugins > plugins you add for the organization | Partially supported in Claude Science | Plugins you set to **Installed by default** or **Required** are synced to members' Claude Science app, which loads their skills and connectors. Plugins left as **Available to install** aren't offered in the app, and plugin commands don't apply there. Which Featured connectors and skills members can use, and whether they can add their own, are separate controls on the **Claude Science** page (see [Featured connectors and skills](#featured-connectors-and-skills), [Custom connectors](#custom-connectors), and [Custom skills](#custom-skills)). |
219| Connectors > Tunnels API (Enterprise) | Partially supported in Claude Science | A connector your organization serves through a tunnel works in the app the same way it does in claude.ai, because the app reaches the connectors on your **Connectors** page through Anthropic's hosted connector service. Custom connectors a member adds in the Claude Science app connect directly from the member's computer and never use a tunnel (admins can restrict this in [Custom connectors](#custom-connectors)). |
220| Connectors > connectors members add themselves | Supported in Claude Science | In claude.ai, members use only the connectors on your **Connectors** page. In Claude Science, members can also add custom connectors (a server URL or a local command) while the **Allow custom connectors** switch is on, which it is by default for Team and not for Enterprise, and the **Connectors** page and its restrictions don't apply to those. Turn off the **Allow custom connectors** switch under **Organization settings** > **Claude Science** to limit members to Featured connectors and the connectors you add on your **Connectors** page (see [Custom connectors](#custom-connectors)). |
221| Connectors > Desktop extension allowlist | Not applicable in Claude Science | Claude Science doesn't install desktop extensions, so there is nothing for this setting to govern. |
222222
223223### Data and privacy
224224
225| Setting in claude.ai | Status for Claude Science | Note |
226| -------------------------------------------------------------------------------------------------------- | ------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
227| Data and privacy > Encryption keys (customer-managed keys) | Supported in Claude Science | The content Anthropic stores from Claude Science (model-call logs, skills members publish, and, where the Compliance API is enabled, session transcripts) is encrypted under your key. Data stored on the member's computer isn't hosted by Anthropic, and work members send to their own SSH hosts, Modal account, or scientific model endpoints doesn't pass through Anthropic, so neither is under your key. In organizations that use customer-managed encryption keys, the app also hides its response rating buttons and feedback form, as claude.ai does. See [Customer-managed encryption keys](/docs/claude-science/how-claude-science-works-with-your-data#customer-managed-encryption-keys). |
228| Data and privacy > Data residency (US-only inference), or the regional processing terms in your contract | Supported in Claude Science | Governs where Anthropic processes Claude Science requests to Claude, as for your other Claude products. It doesn't cover code that runs on the member's computer, SSH hosts, or Modal account (the same boundary as Claude Code). |
229| Data and privacy > HIPAA Compliance | Not applicable in Claude Science | Organizations with HIPAA compliance enabled can turn Claude Science on, but its use isn't covered under your BAA and members must keep protected health information out of it. These organizations start from stricter defaults, listed under [Defaults by plan](#defaults-by-plan). |
230| Data and privacy > Retention period for chats and projects (Enterprise) | Partially supported in Claude Science | The window doesn't reach data stored on members' computers. For Enterprise organizations with the Compliance API enabled, Anthropic keeps each Claude Science session transcript it captures for the window in effect at the time of capture, or for 6 years when no window is set. See [How Claude Science works with your data](/docs/claude-science/how-claude-science-works-with-your-data) for what Anthropic keeps and for how long. |
225| Setting in claude.ai | Status for Claude Science | Note |
226| - | - | - |
227| Data and privacy > Encryption keys (customer-managed keys) | Supported in Claude Science | The content Anthropic stores from Claude Science (model-call logs, skills members publish, and, where the Compliance API is enabled, session transcripts) is encrypted under your key. Data stored on the member's computer isn't hosted by Anthropic, and work members send to their own SSH hosts, Modal account, or scientific model endpoints doesn't pass through Anthropic, so neither is under your key. In organizations that use customer-managed encryption keys, the app also hides its response rating buttons and feedback form, as claude.ai does. See [Customer-managed encryption keys](/docs/claude-science/how-claude-science-works-with-your-data#customer-managed-encryption-keys). |
228| Data and privacy > Data residency (US-only inference), or the regional processing terms in your contract | Supported in Claude Science | Governs where Anthropic processes Claude Science requests to Claude, as for your other Claude products. It doesn't cover code that runs on the member's computer, SSH hosts, or Modal account (the same boundary as Claude Code). |
229| Data and privacy > HIPAA Compliance | Not applicable in Claude Science | Organizations with HIPAA compliance enabled can turn Claude Science on, but its use isn't covered under your BAA and members must keep protected health information out of it. These organizations start from stricter defaults, listed under [Defaults by plan](#defaults-by-plan). |
230| Data and privacy > Retention period for chats and projects (Enterprise) | Partially supported in Claude Science | The window doesn't reach data stored on members' computers. For Enterprise organizations with the Compliance API enabled, Anthropic keeps each Claude Science session transcript it captures for the window in effect at the time of capture, or for 6 years when no window is set. See [How Claude Science works with your data](/docs/claude-science/how-claude-science-works-with-your-data) for what Anthropic keeps and for how long. |
231231
232232### Audit and compliance
233233
234| Setting in claude.ai | Status for Claude Science | Note |
235| ------------------------------------ | ------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
236| Data and privacy > Export audit logs | Not available in Claude Science | Claude Science doesn't write events to the audit log. For Enterprise organizations with the Compliance API enabled, changes to your Claude Science organization settings are recorded in its Activity Feed instead. |
237| Data and privacy > Compliance API | Supported in Claude Science | Enterprise plans only. The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) returns read-only transcripts of members' Claude Science sessions (this coverage is in beta) and records changes to your Claude Science organization settings in its Activity Feed. Sessions in organizations with HIPAA compliance enabled aren't captured. See [Compliance API coverage](/docs/claude-science/how-claude-science-works-with-your-data#compliance-api-coverage). |
238| Data and privacy > Export data | Not available in Claude Science | The organization export doesn't include Claude Science conversations and files, which are stored on members' computers (the same as Claude Code). |
234| Setting in claude.ai | Status for Claude Science | Note |
235| - | - | - |
236| Data and privacy > Export audit logs | Not available in Claude Science | Claude Science doesn't write events to the audit log. For Enterprise organizations with the Compliance API enabled, changes to your Claude Science organization settings are recorded in its Activity Feed instead. |
237| Data and privacy > Compliance API | Supported in Claude Science | Enterprise plans only. The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) returns read-only transcripts of members' Claude Science sessions (this coverage is in beta) and records changes to your Claude Science organization settings in its Activity Feed. Sessions in organizations with HIPAA compliance enabled aren't captured. See [Compliance API coverage](/docs/claude-science/how-claude-science-works-with-your-data#compliance-api-coverage). |
238| Data and privacy > Export data | Not available in Claude Science | The organization export doesn't include Claude Science conversations and files, which are stored on members' computers (the same as Claude Code). |
239239
240240### Usage, models, and billing
241241
242| Setting in claude.ai | Status for Claude Science | Note |
243| ---------------------------------------------------- | --------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
244| Usage > Extra usage and Spend limits | Supported in Claude Science | Claude Science usage counts toward each member's 5-hour and weekly usage limits, in the same pool as Claude Code and Cowork. |
245| Billing | Supported in Claude Science | Claude Science uses the same seat as the rest of claude.ai, so there is nothing separate to purchase. |
242| Setting in claude.ai | Status for Claude Science | Note |
243| - | - | - |
244| Usage > Extra usage and Spend limits | Supported in Claude Science | Claude Science usage counts toward each member's 5-hour and weekly usage limits, in the same pool as Claude Code and Cowork. |
245| Billing | Supported in Claude Science | Claude Science uses the same seat as the rest of claude.ai, so there is nothing separate to purchase. |
246246| Models > Model access and Default model (Enterprise) | Supported in Claude Science | Claude Science follows your **Models** page. Turning a model off, for the whole organization or for a custom role, removes it from those members' model picker in the app within a few minutes, and requests for that model are refused. Your **Default model** setting applies in the app as it does in claude.ai. Team plans don't have the **Models** page. |
247| Analytics (from the user menu) | Supported in Claude Science | Analytics has a **Claude Science** tab with adoption and session metrics, and the spend charts on the **Overview** tab can be filtered to Claude Science (see [Monitor usage](/docs/claude-science/monitor-usage)). |
247| Analytics (from the user menu) | Supported in Claude Science | Analytics has a **Claude Science** tab with adoption and session metrics, and the spend charts on the **Overview** tab can be filtered to Claude Science (see [Monitor usage](/docs/claude-science/monitor-usage)). |
248248
249249### Offboarding and local data
250250
251| Setting in claude.ai | Status for Claude Science | Note |
252| ------------------------------ | ------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
253| Removing a member (local data) | Not available in Claude Science | Removing a member ends their access to Claude Science but doesn't delete data already on their computer. Use your device management software for that (see [Manage on devices](/docs/claude-science/manage-on-devices)). |
254| Deleting local data | Not available in Claude Science | When a member deletes Claude Science data on their computer, nothing Anthropic holds is deleted: the model-call logs and, where captured, Compliance API session transcripts remain until their own retention periods end (see [How Claude Science works with your data](/docs/claude-science/how-claude-science-works-with-your-data)). |
251| Setting in claude.ai | Status for Claude Science | Note |
252| - | - | - |
253| Removing a member (local data) | Not available in Claude Science | Removing a member ends their access to Claude Science but doesn't delete data already on their computer. Use your device management software for that (see [Manage on devices](/docs/claude-science/manage-on-devices)). |
254| Deleting local data | Not available in Claude Science | When a member deletes Claude Science data on their computer, nothing Anthropic holds is deleted: the model-call logs and, where captured, Compliance API session transcripts remain until their own retention periods end (see [How Claude Science works with your data](/docs/claude-science/how-claude-science-works-with-your-data)). |
255255
claude-science/changelog Changed · +10 / -0 lines
from line 2
22
33> Release notes for Claude Science, including new features, improvements, and bug fixes by version.
44
5<Update label="0.1.54" description="September 28, 2026">
6 * Sessions on Claude Sonnet 5.5 now default to Extra high reasoning effort
7 * Windows: after an update, the app window reopens on the new version by itself
8 * Pinned artifacts (formerly starred) and pinned projects now show a pushpin instead of a star
9 * Editing a Markdown table cell now outlines the cell itself instead of opening a box over it
10 * The app starts much faster with a long list of allowed domains
11 * Security hardening of the analysis sandbox on Mac, Windows, and Linux
12 * Various bug fixes and security improvements
13</Update>
14
515<Update label="0.1.53" description="September 24, 2026">
616 * Paste a list of domains in **Settings > Network** to allow them all at once
717 * In Markdown files, editing table cells in place now works in files with up to 2,500 table cells, however long their text
claude-science/command-line-settings Changed · +28 / -28 lines
from line 7
77
88## Commands
99
10| Command | What it does |
11| ----------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
12| `claude-science serve` | Start the background program and open the web app in your browser at a single-use login link. One runs per data directory; Ctrl-C stops it. |
13| `claude-science open` | Mint a fresh login link from the running program and open it in your browser. |
14| `claude-science url` | Print a fresh login link alone on standard output and nothing else. |
15| `claude-science status` | Print whether the program is running, the version, and the port, as JSON. |
16| `claude-science logs` | Print the newest log file from the data directory. `--tail` follows it live. |
17| `claude-science stop` | Stop the program cleanly. |
18| `claude-science update` | Check for and install an update. `--check` only reports; --to `<version>` installs a specific version, which is also how you roll back. Updates are signature-verified and replace the binary atomically. |
19| `claude-science import` `<path>` | Merge another data directory, or its database file, into this one. |
20| `claude-science uninstall` | Windows only. Remove the app, its shortcuts, and its PATH entry while keeping your data; `--purge` also deletes the data directory. Quit Claude Science first. |
21| `claude-science --version` | Print the version. |
22| `claude-science` `<command>` --help | Print help for any command. |
10| Command | What it does |
11| - | - |
12| `claude-science serve` | Start the background program and open the web app in your browser at a single-use login link. One runs per data directory; Ctrl-C stops it. |
13| `claude-science open` | Mint a fresh login link from the running program and open it in your browser. |
14| `claude-science url` | Print a fresh login link alone on standard output and nothing else. |
15| `claude-science status` | Print whether the program is running, the version, and the port, as JSON. |
16| `claude-science logs` | Print the newest log file from the data directory. `--tail` follows it live. |
17| `claude-science stop` | Stop the program cleanly. |
18| `claude-science update` | Check for and install an update. `--check` only reports; --to `<version>` installs a specific version, which is also how you roll back. Updates are signature-verified and replace the binary atomically. |
19| `claude-science import` `<path>` | Merge another data directory, or its database file, into this one. |
20| `claude-science uninstall` | Windows only. Remove the app, its shortcuts, and its PATH entry while keeping your data; `--purge` also deletes the data directory. Quit Claude Science first. |
21| `claude-science --version` | Print the version. |
22| `claude-science` `<command>` --help | Print help for any command. |
2323
2424<Note>
2525 `import` has no preview and no undo. Back up the data directory before you run it; running the same import a second time is safe.
from line 29
2929
3030These two work on every command. On Windows, `~` in the defaults below is your user profile folder, `%USERPROFILE%`.
3131
32| Flag | Default | What it does |
33| -------------------- | ------------------------------- | ------------------------------- |
34| `--data-dir` `<dir>` | `~/.claude-science` | The data directory to use. |
35| `--config` `<file>` | `~/.claude-science/config.toml` | The configuration file to read. |
32| Flag | Default | What it does |
33| - | - | - |
34| `--data-dir` `<dir>` | `~/.claude-science` | The data directory to use. |
35| `--config` `<file>` | `~/.claude-science/config.toml` | The configuration file to read. |
3636
3737## The login link
3838
from line 41
4141
4242## Flags for serve
4343
44| Flag | Default | What it does |
45| ------------------------- | --------- | ------------------------------------------------------------------------------------------------------------------------------- |
46| `--port` `<n>` | `8000` | The port the web app is served on. 0 picks a free port. |
47| `--no-browser` | off | Do not open a browser. url prints a login link any time you want one. |
48| `--detached` | off | Run in the background. Implies --no-browser. |
49| `--no-auto-update` | off | Do not check for or install updates. For a pinned or centrally managed install. |
50| `--host` `<address>` | 127.0.0.1 | The address the app listens on. Anything else exposes the app to your network; prefer an SSH tunnel. |
51| `--base-path` `</prefix>` | unset | Serve the app under a URL prefix behind a reverse proxy. |
52| `--allow-origin` `<url>` | unset | An extra browser Origin allowed to connect; repeat the flag for more than one. It does not change which sites Claude can reach. |
53| `--sandbox-port` `<n>` | port + 1 | The separate origin that previews of generated HTML are served from, so a previewed page cannot read your session. |
54| `--verbose` | off | Show startup and info log lines on the console; by default they go only to the log file. |
44| Flag | Default | What it does |
45| - | - | - |
46| `--port` `<n>` | `8000` | The port the web app is served on. 0 picks a free port. |
47| `--no-browser` | off | Do not open a browser. url prints a login link any time you want one. |
48| `--detached` | off | Run in the background. Implies --no-browser. |
49| `--no-auto-update` | off | Do not check for or install updates. For a pinned or centrally managed install. |
50| `--host` `<address>` | 127.0.0.1 | The address the app listens on. Anything else exposes the app to your network; prefer an SSH tunnel. |
51| `--base-path` `</prefix>` | unset | Serve the app under a URL prefix behind a reverse proxy. |
52| `--allow-origin` `<url>` | unset | An extra browser Origin allowed to connect; repeat the flag for more than one. It does not change which sites Claude can reach. |
53| `--sandbox-port` `<n>` | port + 1 | The separate origin that previews of generated HTML are served from, so a previewed page cannot read your session. |
54| `--verbose` | off | Show startup and info log lines on the console; by default they go only to the log file. |
5555
5656## Dangerous flags
5757
claude-science/configuration-file-reference Changed · +18 / -18 lines
from line 14
1414
1515The `[network]` table configures the app's own connections.
1616
17| Key | Type | Default | Effect |
18| ----------------- | ------------------------------------ | -------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
19| `proxy` | string (URL) | unset | The outbound proxy for the app's HTTP and HTTPS connections, for example `http://proxy.example.corp:8080`. Supply Basic-authentication credentials in the address. An `https://` (TLS-to-proxy) address applies to the app's own connections only; sandboxed package downloads connect directly when the proxy is `https://`, so prefer `http://`. A proxy variable in the app's environment (including `ALL_PROXY`) takes precedence over this key, which takes precedence over the Settings proxy field and the proxy detected from macOS or Windows system settings. |
20| `no_proxy` | string (comma-separated) | unset | Hosts that bypass the proxy, as exact hostnames or domain suffixes in one comma-separated string, for example `".example.corp,registry.example.corp"`. Combined with the `NO_PROXY` environment variable and, when the macOS or Windows system settings supply the proxy address, the system's bypass list. Loopback addresses always bypass the proxy. |
21| `ca_bundle` | string (absolute path) | unset | PEM file added to the app's default TLS trust for sign-in, the Claude API, Anthropic-hosted connectors, update checks, and [cloud storage](/docs/claude-science/cloud-storage) access from Settings (Amazon S3, S3-compatible stores, and Google Cloud Storage with an HMAC key); use it for a corporate root behind TLS inspection. It covers the app's own connections only, while package downloads use `[conda] ca_bundle`. The value must be an absolute path outside the app's data directory (`~/.claude-science`), temporary directories, and any directory you have granted Claude write access to; a system location such as `/etc/claude-science/corporate-ca.pem`, or a folder under `C:\ProgramData` on Windows, is recommended. The file must exist, parse as a PEM bundle, and contain no private key; a failing value is ignored with a warning. On Windows, when this key and `[conda] ca_bundle` are both unset, the roots in the computer's Trusted Root Certification Authorities store are trusted automatically instead. |
22| `mcp_x509_strict` | `"auto"`, `"relaxed"`, or `"strict"` | `"auto"` | How strictly local connectors check a corporate certificate's profile. With `"auto"`, Claude Science relaxes the strict check when it detects TLS inspection from a configured `[network] ca_bundle`. Connectors pick up a change at their next relaunch. |
17| Key | Type | Default | Effect |
18| - | - | - | - |
19| `proxy` | string (URL) | unset | The outbound proxy for the app's HTTP and HTTPS connections, for example `http://proxy.example.corp:8080`. Supply Basic-authentication credentials in the address. An `https://` (TLS-to-proxy) address applies to the app's own connections only; sandboxed package downloads connect directly when the proxy is `https://`, so prefer `http://`. A proxy variable in the app's environment (including `ALL_PROXY`) takes precedence over this key, which takes precedence over the Settings proxy field and the proxy detected from macOS or Windows system settings. |
20| `no_proxy` | string (comma-separated) | unset | Hosts that bypass the proxy, as exact hostnames or domain suffixes in one comma-separated string, for example `".example.corp,registry.example.corp"`. Combined with the `NO_PROXY` environment variable and, when the macOS or Windows system settings supply the proxy address, the system's bypass list. Loopback addresses always bypass the proxy. |
21| `ca_bundle` | string (absolute path) | unset | PEM file added to the app's default TLS trust for sign-in, the Claude API, Anthropic-hosted connectors, update checks, and [cloud storage](/docs/claude-science/cloud-storage) access from Settings (Amazon S3, S3-compatible stores, and Google Cloud Storage with an HMAC key); use it for a corporate root behind TLS inspection. It covers the app's own connections only, while package downloads use `[conda] ca_bundle`. The value must be an absolute path outside the app's data directory (`~/.claude-science`), temporary directories, and any directory you have granted Claude write access to; a system location such as `/etc/claude-science/corporate-ca.pem`, or a folder under `C:\ProgramData` on Windows, is recommended. The file must exist, parse as a PEM bundle, and contain no private key; a failing value is ignored with a warning. On Windows, when this key and `[conda] ca_bundle` are both unset, the roots in the computer's Trusted Root Certification Authorities store are trusted automatically instead. |
22| `mcp_x509_strict` | `"auto"`, `"relaxed"`, or `"strict"` | `"auto"` | How strictly local connectors check a corporate certificate's profile. With `"auto"`, Claude Science relaxes the strict check when it detects TLS inspection from a configured `[network] ca_bundle`. Connectors pick up a change at their next relaunch. |
2323
2424### Package download keys
2525
2626The `[conda]` table configures where analysis environments fetch packages from and how those downloads verify certificates.
2727
28| Key | Type | Default | Effect |
29| ----------------------- | ---------------------- | ------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
30| `channel_mirror` | string (URL) | unset | Base URL of an internal conda mirror. Channel names resolve beneath it, so `<channel_mirror>/conda-forge/noarch/repodata.json` must return the conda-forge index. Setting it removes the public conda hosts from the sandbox allowlist and admits the mirror host, which environment builds contact directly from the workstation, not through an outbound proxy. Must be `https://` on port 443 or 8443 (an `http://` URL is accepted only when `allow_insecure_mirror` is set), by DNS name, with no embedded credentials. A deployed value these rules reject prevents the app from starting. An [organization package mirror](/docs/claude-science/admin-controls#organization-package-mirror) set under **Organization settings** > **Claude Science** takes precedence over this key. |
31| `pip_index_url` | string (URL) | unset | A PEP 503 simple index for Python packages, for example an Artifactory or Nexus PyPI remote ending in `/simple`. Setting it removes the public Python hosts from the sandbox allowlist. Same URL rules as `channel_mirror`, including the startup failure on an invalid value, and the same precedence of an organization package mirror. |
32| `ca_bundle` | string (absolute path) | unset | A complete PEM bundle (public roots plus your corporate roots) that package downloads verify against, replacing the default trust list; in this release the bundle alone may not be sufficient for pip, which verifies against the operating system's trust store. On macOS and Linux this key affects package downloads only, and it never fixes sign-in; behind TLS inspection, set `[network] ca_bundle` as well. When unset, Linux uses your distribution's system certificate bundle. On Windows, package downloads verify against the Windows certificate store and do not read this key; leave it unset there unless you need a custom bundle, because a file set on Windows becomes the complete certificate list that code inside sessions trusts and turns off the app's automatic use of the Windows certificate store. Same path rules as `[network] ca_bundle`. |
33| `allow_insecure_mirror` | boolean | `false` | Allows `http://` mirror URLs in this file (the Settings page accepts `https://` only). Off by default because a plaintext mirror lets an on-path attacker substitute packages. |
34| `ssl_no_revoke` | boolean | `true` | Windows only. When `true`, conda package downloads skip the certificate-revocation check, which networks that inspect TLS usually cannot answer. Set it to `false` to require the check, so that a revoked or uncheckable certificate is rejected. pip downloads and the app's own connections are unaffected. |
28| Key | Type | Default | Effect |
29| - | - | - | - |
30| `channel_mirror` | string (URL) | unset | Base URL of an internal conda mirror. Channel names resolve beneath it, so `<channel_mirror>/conda-forge/noarch/repodata.json` must return the conda-forge index. Setting it removes the public conda hosts from the sandbox allowlist and admits the mirror host, which environment builds contact directly from the workstation, not through an outbound proxy. Must be `https://` on port 443 or 8443 (an `http://` URL is accepted only when `allow_insecure_mirror` is set), by DNS name, with no embedded credentials. A deployed value these rules reject prevents the app from starting. An [organization package mirror](/docs/claude-science/admin-controls#organization-package-mirror) set under **Organization settings** > **Claude Science** takes precedence over this key. |
31| `pip_index_url` | string (URL) | unset | A PEP 503 simple index for Python packages, for example an Artifactory or Nexus PyPI remote ending in `/simple`. Setting it removes the public Python hosts from the sandbox allowlist. Same URL rules as `channel_mirror`, including the startup failure on an invalid value, and the same precedence of an organization package mirror. |
32| `ca_bundle` | string (absolute path) | unset | A complete PEM bundle (public roots plus your corporate roots) that package downloads verify against, replacing the default trust list; in this release the bundle alone may not be sufficient for pip, which verifies against the operating system's trust store. On macOS and Linux this key affects package downloads only, and it never fixes sign-in; behind TLS inspection, set `[network] ca_bundle` as well. When unset, Linux uses your distribution's system certificate bundle. On Windows, package downloads verify against the Windows certificate store and do not read this key; leave it unset there unless you need a custom bundle, because a file set on Windows becomes the complete certificate list that code inside sessions trusts and turns off the app's automatic use of the Windows certificate store. Same path rules as `[network] ca_bundle`. |
33| `allow_insecure_mirror` | boolean | `false` | Allows `http://` mirror URLs in this file (the Settings page accepts `https://` only). Off by default because a plaintext mirror lets an on-path attacker substitute packages. |
34| `ssl_no_revoke` | boolean | `true` | Windows only. When `true`, conda package downloads skip the certificate-revocation check, which networks that inspect TLS usually cannot answer. Set it to `false` to require the check, so that a revoked or uncheckable certificate is rejected. pip downloads and the app's own connections are unaffected. |
3535
3636### Sandbox network keys
3737
3838The `[sandbox.network]` table adjusts the network allowlist the analysis sandbox enforces. Members see the same allowlist under **Settings** > **Network**.
3939
40| Key | Type | Default | Effect |
41| ----------------- | ---------------- | ------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
42| `enabled` | boolean | `true` | When `false`, code Claude runs has no network access: package installs and data fetches inside the analysis fail, while the app's own connections are unaffected. This is a no-network mode, not a way to skip the allowlist. |
43| `allowed_domains` | array of strings | `[]` | Domains added to the built-in allowlist, as exact hostnames or wildcards such as `*.example.org`. While the organization manages the [network allowlist](/docs/claude-science/admin-controls#network-allowlist) under **Organization settings** > **Claude Science**, these domains are set aside and the organization's list applies. |
44| `denied_domains` | array of strings | `[]` | Domains added to the built-in denylist. A denied domain is blocked even if it also appears on the allowlist, and the built-in denylist entries cannot be removed. |
40| Key | Type | Default | Effect |
41| - | - | - | - |
42| `enabled` | boolean | `true` | When `false`, code Claude runs has no network access: package installs and data fetches inside the analysis fail, while the app's own connections are unaffected. This is a no-network mode, not a way to skip the allowlist. |
43| `allowed_domains` | array of strings | `[]` | Domains added to the built-in allowlist, as exact hostnames or wildcards such as `*.example.org`. While the organization manages the [network allowlist](/docs/claude-science/admin-controls#network-allowlist) under **Organization settings** > **Claude Science**, these domains are set aside and the organization's list applies. |
44| `denied_domains` | array of strings | `[]` | Domains added to the built-in denylist. A denied domain is blocked even if it also appears on the allowlist, and the built-in denylist entries cannot be removed. |
4545
4646## Related resources
4747
claude-science/connectors-and-skills Changed · +18 / -18 lines
from line 8
88
99Claude Science includes Featured connectors to public life-sciences databases. They're on by default and can be turned off individually in **Settings > Connectors**. On Team and Enterprise plans, your organization can also turn individual Featured connectors off for everyone, and in organizations with HIPAA compliance enabled they start off until an admin turns them on. A connector your organization has off stays listed, grayed, and Claude can't use it (see [Featured connectors and skills](/docs/claude-science/admin-controls#featured-connectors-and-skills)). Featured connectors are read-only and don't require an account or key. Some underlying databases have non-commercial or attribution terms; review each source's license for your use case.
1010
11| Connector | Sources |
12| ------------------------- | ---------------------------------------------- |
13| Genomes | Ensembl (incl. VEP), UCSC |
14| Genes & Ontologies | MyGene, UniProt, GO, Reactome, OLS |
15| Variants | gnomAD, ClinVar, dbSNP |
16| Human Genetics | GWAS Catalog, FinnGen, BioBank Japan |
17| Clinical Genomics | ClinGen, CIViC, Open Targets |
18| Expression | GTEx |
19| Regulation | JASPAR, UniBind |
20| Protein Annotation | InterPro, Pfam, Human Protein Atlas, STRING |
21| Structures & Interactions | PDB, AlphaFold, EMDB, Complex Portal, IntAct |
22| RNA | Rfam |
23| Omics Archives | GEO, ArrayExpress, PRIDE, MGnify, MetaboLights |
24| Cancer Models | cBioPortal |
25| Chemistry | PubChem, ChEBI, Rhea, BindingDB |
26| Drug Regulatory | FDA drug data, openFDA |
27| Literature Graph | OpenAlex, arXiv |
28| Research Resources | Grants.gov, Antibody Registry |
11| Connector | Sources |
12| - | - |
13| Genomes | Ensembl (incl. VEP), UCSC |
14| Genes & Ontologies | MyGene, UniProt, GO, Reactome, OLS |
15| Variants | gnomAD, ClinVar, dbSNP |
16| Human Genetics | GWAS Catalog, FinnGen, BioBank Japan |
17| Clinical Genomics | ClinGen, CIViC, Open Targets |
18| Expression | GTEx |
19| Regulation | JASPAR, UniBind |
20| Protein Annotation | InterPro, Pfam, Human Protein Atlas, STRING |
21| Structures & Interactions | PDB, AlphaFold, EMDB, Complex Portal, IntAct |
22| RNA | Rfam |
23| Omics Archives | GEO, ArrayExpress, PRIDE, MGnify, MetaboLights |
24| Cancer Models | cBioPortal |
25| Chemistry | PubChem, ChEBI, Rhea, BindingDB |
26| Drug Regulatory | FDA drug data, openFDA |
27| Literature Graph | OpenAlex, arXiv |
28| Research Resources | Grants.gov, Antibody Registry |
2929
3030Additional Featured connectors: **BioMart**, **CellGuide** (CELLxGENE cell types), **ZINC** (purchasable chemical space), and **Ketcher Chemistry** (2D molecule sketcher).
3131
claude-science/core-concepts Changed · +8 / -8 lines
from line 22
2222
2323A permission card appears in the conversation each time Claude needs a new kind of access. The card names exactly what's being requested. You can allow or deny each one.
2424
25| Action | Card title | Scope options |
26| ---------------------- | --------------------------------------------------------------------------------------------------------------- | ------------------------------------------------- |
27| Read or write a folder | Access `<folder>` on your computer? | Read-only or Read & write; persists until revoked |
28| Run code | Run Python code? / Run R code? / Run a shell command? / Run a PowerShell command? (Windows) / Install packages? | Once, This conversation, This project, or Global |
29| Reach a network host | Connect to `<target>`? | Persists until revoked |
30| Use a connector tool | Use `<tool>`? | Once, This conversation, This project, or Global |
31| Use a saved credential | Credentials | Once, This conversation, This project, or Global |
32| Run a remote job | Run this job on `<host>`? / Start a Modal job? | Once, This conversation, This project, or Global |
25| Action | Card title | Scope options |
26| - | - | - |
27| Read or write a folder | Access `<folder>` on your computer? | Read-only or Read & write; persists until revoked |
28| Run code | Run Python code? / Run R code? / Run a shell command? / Run a PowerShell command? (Windows) / Install packages? | Once, This conversation, This project, or Global |
29| Reach a network host | Connect to `<target>`? | Persists until revoked |
30| Use a connector tool | Use `<tool>`? | Once, This conversation, This project, or Global |
31| Use a saved credential | Credentials | Once, This conversation, This project, or Global |
32| Run a remote job | Run this job on `<host>`? / Start a Modal job? | Once, This conversation, This project, or Global |
3333
3434All standing grants are listed in Settings > Permissions and can be revoked there.
3535
claude-science/corporate-networks Changed · +14 / -14 lines
from line 22
2222
2323## What works on a corporate network
2424
25| Network shape | macOS | Windows | Linux |
26| ---------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
27| Explicit outbound HTTP proxy (HTTP CONNECT) | Supported; detected automatically from the system settings | Supported; detected automatically from Windows proxy settings | Supported |
28| Proxy that requires Basic authentication | Supported, with credentials in the proxy address | Supported, with credentials in the proxy address | Supported, with credentials in the proxy address |
29| Proxy that requires NTLM, Negotiate, or Kerberos authentication | Not supported | Not supported | Not supported |
30| Network that only publishes a PAC or WPAD file | Not supported | Supported in the app window, which follows the proxy the script resolves (see [System proxy settings on macOS and Windows](#system-proxy-settings-on-macos-and-windows)) | Not supported |
31| SOCKS proxy | Not supported | Not supported | Not supported |
32| TLS inspection on the app's own connections (Zscaler, Netskope, and similar) | Supported with a CA bundle setting | Supported; a corporate root in the computer's certificate store is trusted automatically | Supported with a CA bundle setting |
33| TLS inspection on conda package downloads | Supported with a CA bundle setting | Supported automatically through the Windows certificate store | Supported with a CA bundle setting |
34| TLS inspection on pip package downloads | Supported, with the corporate root also installed in the operating system's trust store (see [Corporate root for package downloads](#corporate-root-for-package-downloads)) | Supported automatically through the Windows certificate store | Supported, with the corporate root also installed in the operating system's trust store (see [Corporate root for package downloads](#corporate-root-for-package-downloads)) |
35| Internal package mirror (Artifactory, Nexus) | Supported | Supported | Supported |
36| Internal package mirror reached only through the corporate proxy | Not supported | Not supported | Not supported |
37| Authenticated package mirror | Supported, with the credential saved in Settings | Supported, with the credential saved in Settings | Supported, with the credential saved in Settings |
38| Local connectors (the bundled research tools) behind TLS inspection | Not supported | Not supported | Not supported |
25| Network shape | macOS | Windows | Linux |
26| - | - | - | - |
27| Explicit outbound HTTP proxy (HTTP CONNECT) | Supported; detected automatically from the system settings | Supported; detected automatically from Windows proxy settings | Supported |
28| Proxy that requires Basic authentication | Supported, with credentials in the proxy address | Supported, with credentials in the proxy address | Supported, with credentials in the proxy address |
29| Proxy that requires NTLM, Negotiate, or Kerberos authentication | Not supported | Not supported | Not supported |
30| Network that only publishes a PAC or WPAD file | Not supported | Supported in the app window, which follows the proxy the script resolves (see [System proxy settings on macOS and Windows](#system-proxy-settings-on-macos-and-windows)) | Not supported |
31| SOCKS proxy | Not supported | Not supported | Not supported |
32| TLS inspection on the app's own connections (Zscaler, Netskope, and similar) | Supported with a CA bundle setting | Supported; a corporate root in the computer's certificate store is trusted automatically | Supported with a CA bundle setting |
33| TLS inspection on conda package downloads | Supported with a CA bundle setting | Supported automatically through the Windows certificate store | Supported with a CA bundle setting |
34| TLS inspection on pip package downloads | Supported, with the corporate root also installed in the operating system's trust store (see [Corporate root for package downloads](#corporate-root-for-package-downloads)) | Supported automatically through the Windows certificate store | Supported, with the corporate root also installed in the operating system's trust store (see [Corporate root for package downloads](#corporate-root-for-package-downloads)) |
35| Internal package mirror (Artifactory, Nexus) | Supported | Supported | Supported |
36| Internal package mirror reached only through the corporate proxy | Not supported | Not supported | Not supported |
37| Authenticated package mirror | Supported, with the credential saved in Settings | Supported, with the credential saved in Settings | Supported, with the credential saved in Settings |
38| Local connectors (the bundled research tools) behind TLS inspection | Not supported | Not supported | Not supported |
3939
4040## Point package installs at an internal mirror
4141
claude-science/enable-claude-science Changed · +6 / -6 lines
from line 8
88
99Claude Science is in beta.
1010
11| Plan | Claude Science app access |
12| ----------- | ----------------------------------------- |
13| Team | Off; turn on in **Organization settings** |
14| Enterprise | Off; turn on in **Organization settings** |
15| Pro and Max | On; no admin action needed |
16| Free | Not available |
11| Plan | Claude Science app access |
12| - | - |
13| Team | Off; turn on in **Organization settings** |
14| Enterprise | Off; turn on in **Organization settings** |
15| Pro and Max | On; no admin action needed |
16| Free | Not available |
1717
1818If your organization has HIPAA compliance enabled, Claude Science app access is also off by default. You can turn it on, but usage isn't covered under your Business Associate Agreement (BAA) and the app shouldn't be used with protected health information (PHI). These organizations also start with stricter organization settings (see [HIPAA organizations](#hipaa-organizations)).
1919
claude-science/how-claude-science-works-with-your-data Changed · +4 / -4 lines
from line 12
1212
1313## Where Claude Science data lives
1414
15| Where | What |
16| --------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
17| The computer running Claude Science | Conversation history, project files and artifacts, saved memory, settings, and stored credentials, in a local folder Anthropic doesn't host or sync (see [Manage Claude Science on devices](/docs/claude-science/manage-on-devices)) |
18| Anthropic | The items listed under [What Anthropic receives](#what-anthropic-receives) |
15| Where | What |
16| - | - |
17| The computer running Claude Science | Conversation history, project files and artifacts, saved memory, settings, and stored credentials, in a local folder Anthropic doesn't host or sync (see [Manage Claude Science on devices](/docs/claude-science/manage-on-devices)) |
18| Anthropic | The items listed under [What Anthropic receives](#what-anthropic-receives) |
1919| Services your organization or members connect | Jobs, files, and queries sent to your SSH hosts, your Modal account, scientific model endpoints, cloud storage, and the external services that local (Featured and custom) connectors, sandboxed code, and remote jobs call, directly from the computer or your own compute and without passing through Anthropic (see [Admin controls](/docs/claude-science/admin-controls#organization-settings)) |
2020
2121Sign-in tokens and the credentials members store for compute and cloud storage are encrypted on the computer, and the rest of the local folder relies on operating-system permissions, so apply your full-disk encryption and device management policies to it.
claude-science/literature-access Changed · +8 / -8 lines
from line 14
1414
1515Each credential in the **Literature access (journals, etc.)** form is optional and independent.
1616
17| Credential | Effect |
18| ---------------------------------------------- | ----------------------------------------------------------------------------------- |
19| **Elsevier API key** + institutional token | Enables the Elsevier route (subscription still required) |
20| **Springer Nature API key** | Enables the Springer Nature route |
21| **Semantic Scholar API key** | Speeds the Semantic Scholar step |
22| **NCBI API key** | Raises the PubMed rate limit from 3 to 10 requests per second |
23| **CORE API key** | Saved with your other literature keys. Claude's full-text retrieval doesn't use it. |
24| Institutional **EZproxy URL** + session cookie | Retries publisher links through your library |
17| Credential | Effect |
18| - | - |
19| **Elsevier API key** + institutional token | Enables the Elsevier route (subscription still required) |
20| **Springer Nature API key** | Enables the Springer Nature route |
21| **Semantic Scholar API key** | Speeds the Semantic Scholar step |
22| **NCBI API key** | Raises the PubMed rate limit from 3 to 10 requests per second |
23| **CORE API key** | Saved with your other literature keys. Claude's full-text retrieval doesn't use it. |
24| Institutional **EZproxy URL** + session cookie | Retries publisher links through your library |
2525
2626OpenAlex has its own entry in the same **Services** list: add a free **OpenAlex API key** there (create one on the [OpenAlex API settings page](https://openalex.org/settings/api)). OpenAlex requires a key on every request, so OpenAlex-backed literature search needs one configured.
2727
claude-science/manage-on-devices Changed · +5 / -5 lines
from line 21
2121
2222To set configuration keys organization-wide, deploy the per-member config.toml (at the path given under [Where the app stores data](#where-the-app-stores-data)) through your MDM or endpoint tool. Claude Science doesn't read its settings from a system-level managed-preferences file or registry policy keys, so there's no native MDM configuration channel on any operating system. Deploying the per-member config.toml is the supported approach. The sandbox network allowlist and the package mirror can instead be set once for every member under **Organization settings** > **Claude Science** (see [Organization settings](/docs/claude-science/admin-controls#organization-settings)). The keys most relevant to admins are:
2323
24| Key | Effect |
25| ---------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------- |
26| disable\_telemetry = true | Stops the app from sending product-usage telemetry and error reports to Anthropic. |
27| data\_dir = "`<path>`" | Moves conversations, artifacts, and workspaces to a managed location (for example, a volume your backup tooling covers). |
28| \[update] auto\_update = false | Prevents the app from updating itself; pair with your own distribution channel. |
24| Key | Effect |
25| - | - |
26| disable\_telemetry = true | Stops the app from sending product-usage telemetry and error reports to Anthropic. |
27| data\_dir = "`<path>`" | Moves conversations, artifacts, and workspaces to a managed location (for example, a volume your backup tooling covers). |
28| \[update] auto\_update = false | Prevents the app from updating itself; pair with your own distribution channel. |
2929| \[sandbox.network] enabled = false | Blocks network access from the app's local code-execution sandbox. The similarly named \[sandbox] network\_isolated key does not control this. |
3030
3131The [configuration file reference](/docs/claude-science/configuration-file-reference) documents the network-related keys and their defaults, and [Use Claude Science on a corporate network](/docs/claude-science/corporate-networks) covers the proxy, TLS-inspection, and mirror settings.
claude-science/monitor-usage Changed · +7 / -7 lines
from line 16
1616
1717Per-member metrics (GET /v1/organizations/analytics/users, science\_metrics object):
1818
19| Field | Description |
20| --------------------------- | ------------------------------------------------------------------------------------------------------------- |
21| distinct\_session\_count | Number of distinct Claude Science sessions. Null on aggregated rows where a distinct count can't be computed. |
22| message\_count | Number of messages sent in Claude Science sessions. |
23| delegation\_count | Number of delegations (handoffs to a specialized agent) in Claude Science sessions. |
24| remote\_compute\_job\_count | Number of remote compute jobs launched from Claude Science sessions. |
25| skills\_used\_count | Total number of skill invocations in Claude Science sessions. |
19| Field | Description |
20| - | - |
21| distinct\_session\_count | Number of distinct Claude Science sessions. Null on aggregated rows where a distinct count can't be computed. |
22| message\_count | Number of messages sent in Claude Science sessions. |
23| delegation\_count | Number of delegations (handoffs to a specialized agent) in Claude Science sessions. |
24| remote\_compute\_job\_count | Number of remote compute jobs launched from Claude Science sessions. |
25| skills\_used\_count | Total number of skill invocations in Claude Science sessions. |
2626
2727See the Admin API reference for authentication and the full schema.
2828
claude-science/network-requirements Changed · +44 / -44 lines
from line 12
1212
1313Every Claude Science install makes these connections, which travel through the member's outbound proxy and TLS inspection, so they need the proxy and corporate-certificate settings from the corporate networks page. All are outbound HTTPS on TCP 443.
1414
15| Domain | Required when | Purpose |
16| --------------------------------------- | --------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
17| `claude.ai` | Always | Browser-based sign-in, usage analytics, feature configuration, and the catalog of available connectors |
18| `platform.claude.com` | Always | Completing sign-in (the OAuth token exchange) |
19| `api.anthropic.com` | Always | The Claude API for every request Claude makes, plus account and usage information |
20| `o1158394.ingest.us.sentry.io` | When telemetry is on (the default) | Crash and error reporting (the error type and where it happened in Claude Science's own code, never error messages, conversation content, or research data); blocking it degrades diagnostics only |
21| `*.mcp.claude.com` | When members use the Anthropic-hosted connectors | PubMed, ClinicalTrials.gov, ChEMBL, and bioRxiv connectors |
22| `storage.googleapis.com` | When automatic updates are on | Update manifests and installers |
23| `downloads.claude.ai` | On Windows, at first launch and when an update changes it | The app window engine, the component that displays the app window |
24| `api.github.com`, `codeload.github.com` | When members import skills from a GitHub repository | Fetching the skill repository's contents |
15| Domain | Required when | Purpose |
16| - | - | - |
17| `claude.ai` | Always | Browser-based sign-in, usage analytics, feature configuration, and the catalog of available connectors |
18| `platform.claude.com` | Always | Completing sign-in (the OAuth token exchange) |
19| `api.anthropic.com` | Always | The Claude API for every request Claude makes, plus account and usage information |
20| `o1158394.ingest.us.sentry.io` | When telemetry is on (the default) | Crash and error reporting (the error type and where it happened in Claude Science's own code, never error messages, conversation content, or research data); blocking it degrades diagnostics only |
21| `*.mcp.claude.com` | When members use the Anthropic-hosted connectors | PubMed, ClinicalTrials.gov, ChEMBL, and bioRxiv connectors |
22| `storage.googleapis.com` | When automatic updates are on | Update manifests and installers |
23| `downloads.claude.ai` | On Windows, at first launch and when an update changes it | The app window engine, the component that displays the app window |
24| `api.github.com`, `codeload.github.com` | When members import skills from a GitHub repository | Fetching the skill repository's contents |
2525
2626Custom connectors and remote compute that members add reach whatever hosts they are configured with, so allow those case by case. Installs with telemetry turned off (see [Telemetry](/docs/claude-science/manage-on-devices#telemetry)) send no error reports, and blocking `o1158394.ingest.us.sentry.io` affects only error reporting, not the rest of the app.
2727
from line 29
2929
3030When Claude searches the scientific literature or retrieves full text, the app itself contacts these hosts over its own connections, which pass through your outbound proxy and TLS inspection like the app connections above, so the proxy must allow them even though several are also on the sandbox allowlist. Full-text downloads come from wherever the open-access copy of an article is hosted, so on a network that allows only listed hosts, expect retrieval of some full-text copies to fail; the domains below keep literature search and PubMed retrieval working.
3131
32| Domain | Required when | Purpose |
33| ------------------------------------------------- | ---------------------------------------------------------- | ---------------------------------------------- |
34| `api.unpaywall.org` | When Claude retrieves full text | Locating open-access copies of articles |
35| `doi.org` | When Claude resolves a DOI | DOI resolution |
36| `eutils.ncbi.nlm.nih.gov`, `www.ncbi.nlm.nih.gov` | When Claude searches PubMed | PubMed/PMC article records and full-text files |
37| `api.semanticscholar.org`, `api.crossref.org` | When Claude searches the literature | Scholarly search and citation metadata |
38| `api.openalex.org` | When a member adds an OpenAlex API key | Validating the stored key |
39| `api.elsevier.com`, `api.springernature.com` | Only when the member has stored those publishers' API keys | Publisher full-text APIs |
32| Domain | Required when | Purpose |
33| - | - | - |
34| `api.unpaywall.org` | When Claude retrieves full text | Locating open-access copies of articles |
35| `doi.org` | When Claude resolves a DOI | DOI resolution |
36| `eutils.ncbi.nlm.nih.gov`, `www.ncbi.nlm.nih.gov` | When Claude searches PubMed | PubMed/PMC article records and full-text files |
37| `api.semanticscholar.org`, `api.crossref.org` | When Claude searches the literature | Scholarly search and citation metadata |
38| `api.openalex.org` | When a member adds an OpenAlex API key | Validating the stored key |
39| `api.elsevier.com`, `api.springernature.com` | Only when the member has stored those publishers' API keys | Publisher full-text APIs |
4040
4141## Analysis sandbox domains
4242
from line 48
4848
4949These domains supply Python, R, and system packages when Claude builds an analysis environment. Members can't turn them off. An organization that manages the allowlist can turn the CRAN and Bioconductor, npm, and GitHub domains off, and the PyPI and conda domains off once an organization package mirror replaces them.
5050
51| Domain | Purpose |
52| ----------------------------------------------------------------------------------------- | ----------------------------------------------- |
53| `pypi.org`, `*.pypi.org`, `files.pythonhosted.org` | Python packages from PyPI |
54| `conda.anaconda.org`, `repo.anaconda.com`, `anaconda.org`, `*.anaconda.org`, `*.conda.io` | conda packages |
55| `cran.r-project.org`, `cloud.r-project.org`, `bioconductor.org`, `www.bioconductor.org` | R packages from CRAN and Bioconductor |
56| `registry.npmjs.org` | npm packages for connectors that need them |
57| `github.com`, `*.github.com`, `*.githubusercontent.com` | Tools and packages published as GitHub releases |
51| Domain | Purpose |
52| - | - |
53| `pypi.org`, `*.pypi.org`, `files.pythonhosted.org` | Python packages from PyPI |
54| `conda.anaconda.org`, `repo.anaconda.com`, `anaconda.org`, `*.anaconda.org`, `*.conda.io` | conda packages |
55| `cran.r-project.org`, `cloud.r-project.org`, `bioconductor.org`, `www.bioconductor.org` | R packages from CRAN and Bioconductor |
56| `registry.npmjs.org` | npm packages for connectors that need them |
57| `github.com`, `*.github.com`, `*.githubusercontent.com` | Tools and packages published as GitHub releases |
5858
5959Claude Science itself does not require GitHub; the package manager ships inside the app. The GitHub domains are used only when a package Claude installs is published as a GitHub release or a member imports a skill from a GitHub repository, and blocking them fails only those operations.
6060
from line 66
6666
6767These groups are on by default. Members can turn them off during onboarding or anytime under **Settings** > **Network**. When the organization manages the allowlist, the organization's per-domain switches apply instead.
6868
69| Group | Domains |
70| ------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
71| NCBI and NIH | `*.ncbi.nlm.nih.gov`, `*.nih.gov`, `cactus.nci.nih.gov` |
72| Genomics and biology | `rest.ensembl.org`, `grch37.rest.ensembl.org`, `*.ensembl.org`, `reactome.org`, `*.reactome.org`, `rest.kegg.jp`, `*.kegg.jp`, `cellguide.cellxgene.cziscience.com`, `gnomad.broadinstitute.org`, `gtexportal.org`, `jaspar.elixir.no`, `www.encodeproject.org`, `mygene.info`, `rfam.org`, `www.cbioportal.org`, `sparql.rhea-db.org`, `bindingdb.org`, `www.bindingdb.org`, `r12.finngen.fi`, `pheweb.jp`, `api.genome.ucsc.edu`, `unibind.uio.no` |
73| Proteomics | `rest.uniprot.org`, `*.uniprot.org`, `string-db.org`, `*.string-db.org`, `*.ebi.ac.uk`, `search.foldseek.com`, `rcsb.org`, `*.rcsb.org`, `*.proteinatlas.org` |
74| Literature and citations | `api.semanticscholar.org`, `api.biorxiv.org`, `www.biorxiv.org`, `api.crossref.org`, `doi.org`, `api.openalex.org`, `arxiv.org`, `*.arxiv.org`, `api.grants.gov` |
75| Clinical and pharma | `api.fda.gov`, `clinicaltrials.gov`, `*.clinicaltrials.gov`, `api.clinpgx.org`, `api.platform.opentargets.org`, `cancer.sanger.ac.uk`, `actionability.clinicalgenome.org`, `search.clinicalgenome.org`, `erepo.genome.network`, `civicdb.org`, `www.antibodyregistry.org`, `cartblanche22.docking.org`, `files.docking.org` |
69| Group | Domains |
70| - | - |
71| NCBI and NIH | `*.ncbi.nlm.nih.gov`, `*.nih.gov`, `cactus.nci.nih.gov` |
72| Genomics and biology | `rest.ensembl.org`, `grch37.rest.ensembl.org`, `*.ensembl.org`, `reactome.org`, `*.reactome.org`, `rest.kegg.jp`, `*.kegg.jp`, `cellguide.cellxgene.cziscience.com`, `gnomad.broadinstitute.org`, `gtexportal.org`, `jaspar.elixir.no`, `www.encodeproject.org`, `mygene.info`, `rfam.org`, `www.cbioportal.org`, `sparql.rhea-db.org`, `bindingdb.org`, `www.bindingdb.org`, `r12.finngen.fi`, `pheweb.jp`, `api.genome.ucsc.edu`, `unibind.uio.no` |
73| Proteomics | `rest.uniprot.org`, `*.uniprot.org`, `string-db.org`, `*.string-db.org`, `*.ebi.ac.uk`, `search.foldseek.com`, `rcsb.org`, `*.rcsb.org`, `*.proteinatlas.org` |
74| Literature and citations | `api.semanticscholar.org`, `api.biorxiv.org`, `www.biorxiv.org`, `api.crossref.org`, `doi.org`, `api.openalex.org`, `arxiv.org`, `*.arxiv.org`, `api.grants.gov` |
75| Clinical and pharma | `api.fda.gov`, `clinicaltrials.gov`, `*.clinicaltrials.gov`, `api.clinpgx.org`, `api.platform.opentargets.org`, `cancer.sanger.ac.uk`, `actionability.clinicalgenome.org`, `search.clinicalgenome.org`, `erepo.genome.network`, `civicdb.org`, `www.antibodyregistry.org`, `cartblanche22.docking.org`, `files.docking.org` |
7676
7777### Optional compute integrations
7878
7979These domains matter only when a member turns on the matching integration.
8080
81| Domain | Required when | Purpose |
82| --------------------------------- | ------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
83| `health.api.nvidia.com` | When members enable NVIDIA-hosted BioNeMo inference | NVIDIA's hosted inference endpoint; a member can enter a different endpoint host when connecting BioNeMo under **Settings** > **Compute** |
84| `nvcr.io` | When members run NVIDIA NIM containers locally | Pulling NVIDIA container images |
85| `api.modal.com`, `*.w.modal.host` | When members connect a Modal account for remote compute | Modal's API and its dynamic worker hosts, reached from the member's machine |
81| Domain | Required when | Purpose |
82| - | - | - |
83| `health.api.nvidia.com` | When members enable NVIDIA-hosted BioNeMo inference | NVIDIA's hosted inference endpoint; a member can enter a different endpoint host when connecting BioNeMo under **Settings** > **Compute** |
84| `nvcr.io` | When members run NVIDIA NIM containers locally | Pulling NVIDIA container images |
85| `api.modal.com`, `*.w.modal.host` | When members connect a Modal account for remote compute | Modal's API and its dynamic worker hosts, reached from the member's machine |
8686
8787### Domains the sandbox always blocks
8888
from line 94
9494
9595Sign-in pages and interactive previews load in the member's web browser, so they are governed by your web-filtering policy rather than the outbound proxy or the sandbox allowlist. If your policy blocks these domains, sign-in pages fail to load or interactive previews render blank or broken.
9696
97| Domain | Purpose |
98| ----------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
99| `claude.ai` | The sign-in authorization page |
100| `console.anthropic.com` | The sign-in fallback page, which shows a one-time code the member pastes into the app when the browser cannot return to the app's local callback address |
101| `cdn.jsdelivr.net`, `esm.sh`, `unpkg.com`, `cdnjs.cloudflare.com` | JavaScript display libraries for interactive previews |
102| `3dmol.org`, `3dmol.csb.pitt.edu` | Molecular structure viewer |
103| `*.claudemcpcontent.com` | Isolated frames that display Claude's HTML previews and interactive connector output. A standard desktop install serves these frames from the app's own local address, so this entry matters mainly where members open Claude Science from a non-local address |
97| Domain | Purpose |
98| - | - |
99| `claude.ai` | The sign-in authorization page |
100| `console.anthropic.com` | The sign-in fallback page, which shows a one-time code the member pastes into the app when the browser cannot return to the app's local callback address |
101| `cdn.jsdelivr.net`, `esm.sh`, `unpkg.com`, `cdnjs.cloudflare.com` | JavaScript display libraries for interactive previews |
102| `3dmol.org`, `3dmol.csb.pitt.edu` | Molecular structure viewer |
103| `*.claudemcpcontent.com` | Isolated frames that display Claude's HTML previews and interactive connector output. A standard desktop install serves these frames from the app's own local address, so this entry matters mainly where members open Claude Science from a non-local address |
104104
105105## Related resources
106106
claude-science/run-on-remote-linux-server Changed · +10 / -10 lines
from line 71
7171
7272## Troubleshooting
7373
74| Symptom | What it means |
75| ----------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
76| `command not found: claude-science` | `~/.local/bin` isn't on your PATH yet. Run `. ~/.profile` or open a new terminal. |
77| An error mentioning `bwrap too old` | The server's bubblewrap is older than 0.8.0. Upgrade it, or use a distribution that ships a newer version, such as Ubuntu 24.04 or later. |
78| An error mentioning `cannot create unprivileged user namespaces` | The kernel or an AppArmor profile blocks the sandbox from creating user namespaces; some Ubuntu 24.04 images restrict this. The error message names the exact setting to change for your distribution. |
79| The sign-in link shows an expired-link page | Links are single-use and valid for about three minutes. Run `claude-science url` on the server and open the fresh link; restarting with `claude-science stop` then `claude-science serve --no-browser` also prints one. |
80| Sign-in stops at claude.ai | The redirect couldn't return through the tunnel (choose **Paste code instead**), your account is on the Free plan (an upgrade is required), or your Team or Enterprise organization hasn't [enabled Claude Science](/docs/claude-science/enable-claude-science) yet. |
81| Interactive HTML previews render as static snapshots after a short delay (charts don't respond) | The tunnel isn't forwarding the preview port. Add the second `-L` forward; the preview port is the web app port plus one (8001 by default). |
82| The browser can't reach `localhost:8000` | The tunnel isn't up; rerun the `ssh -L` command. If the tunnel is up, confirm Claude Science is running on the server with `claude-science status`. |
83| The installer reports no binary for your platform | Claude Science on Linux needs x64 with glibc. arm64 servers and musl-based distributions such as Alpine aren't supported. |
74| Symptom | What it means |
75| - | - |
76| `command not found: claude-science` | `~/.local/bin` isn't on your PATH yet. Run `. ~/.profile` or open a new terminal. |
77| An error mentioning `bwrap too old` | The server's bubblewrap is older than 0.8.0. Upgrade it, or use a distribution that ships a newer version, such as Ubuntu 24.04 or later. |
78| An error mentioning `cannot create unprivileged user namespaces` | The kernel or an AppArmor profile blocks the sandbox from creating user namespaces; some Ubuntu 24.04 images restrict this. The error message names the exact setting to change for your distribution. |
79| The sign-in link shows an expired-link page | Links are single-use and valid for about three minutes. Run `claude-science url` on the server and open the fresh link; restarting with `claude-science stop` then `claude-science serve --no-browser` also prints one. |
80| Sign-in stops at claude.ai | The redirect couldn't return through the tunnel (choose **Paste code instead**), your account is on the Free plan (an upgrade is required), or your Team or Enterprise organization hasn't [enabled Claude Science](/docs/claude-science/enable-claude-science) yet. |
81| Interactive HTML previews render as static snapshots after a short delay (charts don't respond) | The tunnel isn't forwarding the preview port. Add the second `-L` forward; the preview port is the web app port plus one (8001 by default). |
82| The browser can't reach `localhost:8000` | The tunnel isn't up; rerun the `ssh -L` command. If the tunnel is up, confirm Claude Science is running on the server with `claude-science status`. |
83| The installer reports no binary for your platform | Claude Science on Linux needs x64 with glibc. arm64 servers and musl-based distributions such as Alpine aren't supported. |
8484
claude-tag/admins/add-connections Changed · +25 / -25 lines
from line 46
4646
4747Read-only connections are most useful in combination: an answer that joins the ticket, the deploy, and the error rate needs all three systems connected. Connecting many systems read-only is a different decision from granting write access anywhere.
4848
49| Connect | Examples | Recommended access | What it adds |
50| :----------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
51| Knowledge and docs | Google Drive, [Notion](/docs/claude-tag/admins/connections/notion), [Confluence](/docs/claude-tag/admins/connections/atlassian) | Read | Answers grounded in design docs, runbooks, and prior decisions |
52| Code | GitHub, [GitLab](/docs/claude-tag/admins/connections/gitlab) | Read and write | On GitHub, branches, pull requests, review, and CI follow-up through the [Claude GitHub App](/docs/claude-tag/admins/configure-github). On GitLab, issues, merge request comments, and pipeline checks through its API |
53| Data warehouse | BigQuery, [Snowflake](/docs/claude-tag/admins/connections/snowflake), Redshift | Read | Data questions answered with charts in the thread; recurring reports |
54| Monitoring | [Sentry](/docs/claude-tag/admins/connections/sentry), [Datadog](/docs/claude-tag/admins/connections/datadog), [PagerDuty](/docs/claude-tag/admins/connections/pagerduty) | Read | Logs, metrics, and errors for debugging and incident work |
55| Issue tracking | [Linear](/docs/claude-tag/admins/connections/linear), [Asana](/docs/claude-tag/admins/connections/asana), [Jira](/docs/claude-tag/admins/connections/atlassian) | Read and write | File tickets and post status updates where work lives |
56| Go-to-market | [HubSpot](/docs/claude-tag/admins/connections/hubspot), [Gong](/docs/claude-tag/admins/connections/gong), [Salesforce](/docs/claude-tag/admins/connections/salesforce) | Read | Pipeline and customer state for account questions |
49| Connect | Examples | Recommended access | What it adds |
50| :- | :- | :- | :- |
51| Knowledge and docs | Google Drive, [Notion](/docs/claude-tag/admins/connections/notion), [Confluence](/docs/claude-tag/admins/connections/atlassian) | Read | Answers grounded in design docs, runbooks, and prior decisions |
52| Code | GitHub, [GitLab](/docs/claude-tag/admins/connections/gitlab) | Read and write | On GitHub, branches, pull requests, review, and CI follow-up through the [Claude GitHub App](/docs/claude-tag/admins/configure-github). On GitLab, issues, merge request comments, and pipeline checks through its API |
53| Data warehouse | BigQuery, [Snowflake](/docs/claude-tag/admins/connections/snowflake), Redshift | Read | Data questions answered with charts in the thread; recurring reports |
54| Monitoring | [Sentry](/docs/claude-tag/admins/connections/sentry), [Datadog](/docs/claude-tag/admins/connections/datadog), [PagerDuty](/docs/claude-tag/admins/connections/pagerduty) | Read | Logs, metrics, and errors for debugging and incident work |
55| Issue tracking | [Linear](/docs/claude-tag/admins/connections/linear), [Asana](/docs/claude-tag/admins/connections/asana), [Jira](/docs/claude-tag/admins/connections/atlassian) | Read and write | File tickets and post status updates where work lives |
56| Go-to-market | [HubSpot](/docs/claude-tag/admins/connections/hubspot), [Gong](/docs/claude-tag/admins/connections/gong), [Salesforce](/docs/claude-tag/admins/connections/salesforce) | Read | Pipeline and customer state for account questions |
5757
5858Per-service instructions, with the credential fields and allowed-websites values, are in the [connection guides](/docs/claude-tag/admins/connections/overview).
5959
from line 63
6363
6464For each tool, create that identity specifically for the agent rather than reusing a shared bot key. The pattern depends on the service.
6565
66| Service type | Recommended pattern |
67| :------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
68| Google Workspace (Drive, Calendar, Docs) | Create a virtual user like `[email protected]` and share the folders and calendars it needs. If using a GCP service-account key with domain-wide delegation, restrict the delegation to that single subject and the minimum OAuth scopes; DWD can otherwise impersonate any user in your domain. |
69| SaaS with native service accounts (Datadog, Snowflake, Sentry) | Create a service account in that tool's admin, scope it to the project or read-only role, and use its API key |
70| SaaS without service accounts (Linear, Asana) | Create a dedicated user seat for the agent and use a personal access token from that seat |
71| Cloud APIs (AWS, GCP) | Create a dedicated IAM principal with the narrowest policy that covers the work |
66| Service type | Recommended pattern |
67| :- | :- |
68| Google Workspace (Drive, Calendar, Docs) | Create a virtual user like `[email protected]` and share the folders and calendars it needs. If using a GCP service-account key with domain-wide delegation, restrict the delegation to that single subject and the minimum OAuth scopes; DWD can otherwise impersonate any user in your domain. |
69| SaaS with native service accounts (Datadog, Snowflake, Sentry) | Create a service account in that tool's admin, scope it to the project or read-only role, and use its API key |
70| SaaS without service accounts (Linear, Asana) | Create a dedicated user seat for the agent and use a personal access token from that seat |
71| Cloud APIs (AWS, GCP) | Create a dedicated IAM principal with the narrowest policy that covers the work |
7272
7373A dedicated account keeps the agent's activity separately auditable in each tool's logs and lets you revoke its access without touching anyone else's. Grant read-only wherever the categories below say read; Claude can never exceed what the key allows.
7474
from line 165
165165
166166For a custom connection, choose the credential type:
167167
168| Credential type | Use for |
169| :------------------------------------------ | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
170| Bearer | API keys and OAuth bearer tokens. Most SaaS REST APIs. |
171| Basic | HTTP Basic authentication. |
172| Body parameter | A token the API expects in the request body or query string instead of a header. |
173| AWS SigV4 | Signed requests to AWS service endpoints with an access key pair. |
174| GCP access token (with Service Account Key) | Google Cloud APIs via a service-account JSON key. Google Workspace services like Drive and Calendar also use this; see [the Google guide](/docs/claude-tag/admins/connections/google). |
175| GCP IAP (with Service Account Key) | Google Cloud services behind Identity-Aware Proxy. |
176| OAuth 2.0 JWT bearer | Server-to-server OAuth. |
177| OAuth 2.0 client credentials | Server-to-server OAuth. Salesforce uses this. |
178| MCP Connector | Sign in once as an admin; the agent acts as that account. The picker offers a fixed set of providers plus the [remote MCP connectors](/docs/connectors/custom/add-unlisted) your organization has added on claude.ai. Other OAuth APIs can't be connected this way. |
168| Credential type | Use for |
169| :- | :- |
170| Bearer | API keys and OAuth bearer tokens. Most SaaS REST APIs. |
171| Basic | HTTP Basic authentication. |
172| Body parameter | A token the API expects in the request body or query string instead of a header. |
173| AWS SigV4 | Signed requests to AWS service endpoints with an access key pair. |
174| GCP access token (with Service Account Key) | Google Cloud APIs via a service-account JSON key. Google Workspace services like Drive and Calendar also use this; see [the Google guide](/docs/claude-tag/admins/connections/google). |
175| GCP IAP (with Service Account Key) | Google Cloud services behind Identity-Aware Proxy. |
176| OAuth 2.0 JWT bearer | Server-to-server OAuth. |
177| OAuth 2.0 client credentials | Server-to-server OAuth. Salesforce uses this. |
178| MCP Connector | Sign in once as an admin; the agent acts as that account. The picker offers a fixed set of providers plus the [remote MCP connectors](/docs/connectors/custom/add-unlisted) your organization has added on claude.ai. Other OAuth APIs can't be connected this way. |
179179
180180For GitHub repositories, use the GitHub connection at [Configure GitHub access](/docs/claude-tag/admins/configure-github) rather than a credential from this table.
181181
claude-tag/admins/attach-to-scope Changed · +19 / -19 lines
from line 18
1818
1919<img className="hidden dark:block" src="https://mintcdn.com/claude-ai/5JFKyLlO7sHMMf5J/images/claude-tag/diagrams/scope-inheritance-dark.svg?fit=max&auto=format&n=5JFKyLlO7sHMMf5J&q=85&s=b53a534b076e6c22f0d86a81841b00a8" alt="Nested boxes. The outermost box is the Default Slack access scope: a bundle attached here is the baseline every channel gets. Inside it, two examples. Outside the workspace box, a channel called another-team in a different workspace gets only the default bundle. Inside the workspace box, which adds an optional bundle for channels inside it, two channel boxes: a public channel called general, with no channel bundle, gets the default plus the workspace bundle; a private channel, marked with a lock, with its own channel bundle, gets all three, the default, workspace, and channel bundles." width="1000" height="320" data-path="images/claude-tag/diagrams/scope-inheritance-dark.svg" />
2020
21| Scope | What it covers | Access |
22| :------------------- | :---------------------------------------- | :---------------------------------------------------------------------- |
23| Default Slack access | Every Slack workspace and channel | The baseline set every channel gets |
24| Workspace | All channels in one Slack workspace | Inherits Default Slack access, plus workspace-level bundles |
25| Channel | A single Slack channel, public or private | Inherits Default Slack access and workspace, plus channel-level bundles |
21| Scope | What it covers | Access |
22| :- | :- | :- |
23| Default Slack access | Every Slack workspace and channel | The baseline set every channel gets |
24| Workspace | All channels in one Slack workspace | Inherits Default Slack access, plus workspace-level bundles |
25| Channel | A single Slack channel, public or private | Inherits Default Slack access and workspace, plus channel-level bundles |
2626
2727The same stacking applies in reverse. Detaching a bundle from a channel removes only that channel's additions, and bundles attached at the workspace or Default Slack access still apply there.
2828
from line 84
8484
8585Each connector or repository row in these sections carries an origin line that says which scope or bundle gave the scope that item.
8686
87| Origin line | What it means |
88| :------------------------- | :------------------------------------------------------------------------------------------------------------------ |
87| Origin line | What it means |
88| :- | :- |
8989| **Inherited from** *scope* | The row comes from a wider scope. When an admin-made bundle carries it, the line adds **via** and the bundle's name |
90| **Attached from** *bundle* | The row was added on this scope through that admin-made bundle |
90| **Attached from** *bundle* | The row was added on this scope through that admin-made bundle |
9191
9292Select the scope name to open that scope, or the bundle name to open the bundle.
9393
from line 123
123123
124124The table lists the kinds of standing instruction that can apply in a channel and who writes each.
125125
126| Layer | Who writes it | Where |
127| :------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------- |
128| Custom instructions | Owner for any scope; channel members and [channel managers](/docs/claude-tag/admins/restrict-access#delegate-channel-setup-to-channel-managers) for the channel scope, unless members are [restricted](#restrict-who-can-set-channel-instructions) | The scope's panel in admin settings, or the **Configure** link in any reply footer for the channel scope |
129| Managed instructions | Full workspace members in one of the channel's [managing channels](/docs/claude-tag/admins/managed-by), which an Owner or Admin selects under **Managed by** on the channel's Configure page | By asking Claude in the managing channel and confirming the card it posts |
130| Channel memory | Anyone in the channel | By telling Claude to remember |
131| Task prompt | The requester | The message itself |
126| Layer | Who writes it | Where |
127| :- | :- | :- |
128| Custom instructions | Owner for any scope; channel members and [channel managers](/docs/claude-tag/admins/restrict-access#delegate-channel-setup-to-channel-managers) for the channel scope, unless members are [restricted](#restrict-who-can-set-channel-instructions) | The scope's panel in admin settings, or the **Configure** link in any reply footer for the channel scope |
129| Managed instructions | Full workspace members in one of the channel's [managing channels](/docs/claude-tag/admins/managed-by), which an Owner or Admin selects under **Managed by** on the channel's Configure page | By asking Claude in the managing channel and confirming the card it posts |
130| Channel memory | Anyone in the channel | By telling Claude to remember |
131| Task prompt | The requester | The message itself |
132132
133133Channel members can shape how Claude responds in their channel through memory, but they can't change which credentials or repositories it has; that's bundle configuration. See [who controls what](/docs/claude-tag/admins/customize) for the full split.
134134
from line 152
152152
153153By default, anyone in a channel who is also a member of your Claude organization can edit that channel's instructions from the **Configure** link in Claude's reply footer. The **Channel member edits** setting in a scope's **Advanced** settings controls this.
154154
155| Option | Effect |
156| :---------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
157| **Inherit** | Follow the parent scope's setting |
158| **Allow** | Members can edit channel instructions from the Configure link |
159| **Block** | Members can't change channel instructions, the channel's default model, or its [**Respond automatically**](/docs/claude-tag/users/when-claude-responds#turn-automatic-replies-on-or-off) setting |
155| Option | Effect |
156| :- | :- |
157| **Inherit** | Follow the parent scope's setting |
158| **Allow** | Members can edit channel instructions from the Configure link |
159| **Block** | Members can't change channel instructions, the channel's default model, or its [**Respond automatically**](/docs/claude-tag/users/when-claude-responds#turn-automatic-replies-on-or-off) setting |
160160
161161A chain of scopes that all inherit resolves to **Allow**. Set **Block** at the workspace or Default Slack access scope to lock channel instructions across every channel beneath it. A [channel manager](/docs/claude-tag/admins/restrict-access#delegate-channel-setup-to-channel-managers) can still edit instructions, change the default model, and switch the **Respond automatically** toggle from the Configure page in a channel assigned to them when **Block** is set.
162162
claude-tag/admins/audit Changed · +4 / -4 lines
from line 21
2121
2222The Audit page, labeled **Activity** in the admin console's left nav and page heading, at [`claude.ai/admin-settings/claude-tag/audit`](https://claude.ai/admin-settings/claude-tag/audit) has these tabs:
2323
24| Tab | What it shows |
25| :----------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
26| **Scheduled work** | Every routine across your organization, with a **Scope** filter and a per-row **⋮** menu (View details, Pause/Resume, Delete) |
27| **Memory** | Each scope's memory files, where you can read what Claude has saved for that workspace or channel. Owners can also edit or delete entries there. |
24| Tab | What it shows |
25| :- | :- |
26| **Scheduled work** | Every routine across your organization, with a **Scope** filter and a per-row **⋮** menu (View details, Pause/Resume, Delete) |
27| **Memory** | Each scope's memory files, where you can read what Claude has saved for that workspace or channel. Owners can also edit or delete entries there. |
2828| **Network events** | An hourly JSON export of the outbound requests Claude made through [Agent Proxy](/docs/claude-tag/concepts/agent-identity#agent-proxy). Git and MCP traffic are not included. Select a date and hour to download. |
2929
3030Each routine on the **Scheduled work** tab shows **Created by** (the member who set it up) in its **View details** dialog. There is no per-action log of every task and who asked; for that, use the trails below.
claude-tag/admins/configure-github Changed · +3 / -3 lines
from line 64
6464
6565When Claude replies "That environment or repo isn't configured for Claude Code", or reports that GitHub returned a 403, check the two levels in order.
6666
67| Check | Where |
68| :---------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
69| The GitHub organization that owns the repository shows **Connected** under **Connected GitHub accounts** | [`claude.ai/admin-settings/github`](https://claude.ai/admin-settings/github). An installation still waiting on a GitHub organization owner shows **Needs permissions**; **Review permissions** opens the approval on github.com. |
67| Check | Where |
68| :- | :- |
69| The GitHub organization that owns the repository shows **Connected** under **Connected GitHub accounts** | [`claude.ai/admin-settings/github`](https://claude.ai/admin-settings/github). An installation still waiting on a GitHub organization owner shows **Needs permissions**; **Review permissions** opens the approval on github.com. |
7070| The repository is listed on the bundle's **Repositories** tab, and that bundle is attached to the channel's scope | [`claude.ai/admin-settings/claude-tag`](https://claude.ai/admin-settings/claude-tag) → **Access bundles** → the bundle → **Repositories**. A repository granted in one bundle isn't reachable from a channel under a different bundle. |
7171
7272Repository grants apply to new threads. After changing the **Repositories** tab, start a fresh thread in the channel and name the repository in the first message.
claude-tag/admins/configure-gitlab Changed · +3 / -3 lines
from line 34
3434
3535Create a [personal access token](https://docs.gitlab.com/user/profile/personal_access_tokens/) for the account. For a GitLab.com service account, create the token from the group's service account settings or through the API; for a regular bot user, sign in as it and create the token from its profile. The token starts with `glpat-`.
3636
37| Scope | When to grant it |
38| :--------- | :------------------------------------------------------------------------------------------------------ |
39| `api` | Read and write. Required for Claude to create and update issues, post comments, and act on pipelines. |
37| Scope | When to grant it |
38| :- | :- |
39| `api` | Read and write. Required for Claude to create and update issues, post comments, and act on pipelines. |
4040| `read_api` | Read-only. Use this instead of `api` if you want Claude to browse and answer questions but never write. |
4141
4242Set an expiry that matches your rotation policy, and store the token somewhere you can retrieve it once; GitLab shows it only at creation.
claude-tag/admins/connections/amplitude Changed · +7 / -7 lines
from line 18
1818
1919On a bundle's **Credentials** tab, clicking **Connect** next to **Amplitude** opens a form that offers two ways to connect: **Sign in with Amplitude**, selected by default, and **Use an API token** below it.
2020
21| Route | What Claude can do | Amplitude data center | What you need |
22| :------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :-------------------- | :--------------------------------------------------------------- |
23| **API key and secret key** (**Use an API token**) | Run analytics queries, such as event segmentation, funnels, and retention, through Amplitude's [Dashboard REST API](https://amplitude.com/docs/apis/analytics/dashboard-rest). The setup steps restrict the key pair to read requests. | US or EU | A project API key and a secret key generated for this connection |
24| **Amplitude sign-in** (**Sign in with Amplitude**) | Work with charts, dashboards, cohorts, and experiments through Amplitude's MCP tools, which can create and edit content as well as read it. Claude acts in Amplitude with the signed-in user's roles and project access. | US | A dedicated Amplitude user to sign in as |
21| Route | What Claude can do | Amplitude data center | What you need |
22| :- | :- | :- | :- |
23| **API key and secret key** (**Use an API token**) | Run analytics queries, such as event segmentation, funnels, and retention, through Amplitude's [Dashboard REST API](https://amplitude.com/docs/apis/analytics/dashboard-rest). The setup steps restrict the key pair to read requests. | US or EU | A project API key and a secret key generated for this connection |
24| **Amplitude sign-in** (**Sign in with Amplitude**) | Work with charts, dashboards, cohorts, and experiments through Amplitude's MCP tools, which can create and edit content as well as read it. Claude acts in Amplitude with the signed-in user's roles and project access. | US | A dedicated Amplitude user to sign in as |
2525
2626Use the API key route when Claude should be limited to read requests. Also use the API key route when Amplitude hosts your organization's data in its EU data center (you sign in to Amplitude at `app.eu.amplitude.com` rather than `app.amplitude.com`), because the **Sign in with Amplitude** option connects to the MCP server for Amplitude's US data center, `https://mcp.amplitude.com/mcp`. Choose Amplitude sign-in when Claude should also build or change content in Amplitude, such as creating a chart or updating a dashboard.
2727
from line 49
4949 <Step title="Enter the key pair">
5050 Select **Use an API token**, then fill in the two fields.
5151
52 | Field | Value |
53 | :------------------ | :----------------------------------------------- |
54 | Claude's API key | The project's API key from Amplitude |
52 | Field | Value |
53 | :- | :- |
54 | Claude's API key | The project's API key from Amplitude |
5555 | Claude's secret key | The secret key you generated for this connection |
5656
5757 The host is prefilled as `amplitude.com`. If Amplitude hosts your organization's data in its EU data center (you sign in to Amplitude at `app.eu.amplitude.com` rather than `app.amplitude.com`), replace the host with `analytics.eu.amplitude.com`.
claude-tag/admins/connections/asana Changed · +3 / -3 lines
from line 22
2222
2323In the bundle, click **Connect** next to **Asana**.
2424
25| Field | Value |
26| :----------------------------- | :----------------------------------- |
25| Field | Value |
26| :- | :- |
2727| Claude's personal access token | The personal access token from Asana |
28| Allowed websites | `app.asana.com` |
28| Allowed websites | `app.asana.com` |
2929
3030The Agent Proxy injects the credential at the network boundary; the model and the sandbox are not given the key. See [how Agent Proxy works](/docs/claude-tag/concepts/agent-identity#agent-proxy).
3131
claude-tag/admins/connections/bigquery Changed · +6 / -6 lines
from line 29
2929
3030In the bundle, click **Connect** next to **Custom tool** and choose **GCP access token (with Service Account Key)**.
3131
32| Field | Value |
33| :----------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
34| Credential type | **GCP access token (with Service Account Key)** |
35| GCP service account key (JSON) | The JSON key file from Google Cloud Console |
36| Scopes (optional) | `https://www.googleapis.com/auth/bigquery`. The field is labeled optional, but leave it empty and the token defaults to a broader scope. BigQuery's query endpoints don't accept a read-only scope; the dataset roles in the section above are what keep the connection read-only. |
37| Allowed websites | `bigquery.googleapis.com` |
32| Field | Value |
33| :- | :- |
34| Credential type | **GCP access token (with Service Account Key)** |
35| GCP service account key (JSON) | The JSON key file from Google Cloud Console |
36| Scopes (optional) | `https://www.googleapis.com/auth/bigquery`. The field is labeled optional, but leave it empty and the token defaults to a broader scope. BigQuery's query endpoints don't accept a read-only scope; the dataset roles in the section above are what keep the connection read-only. |
37| Allowed websites | `bigquery.googleapis.com` |
3838
3939Agent Proxy exchanges the service-account key for an access token and injects it at the network boundary; the model and the sandbox are not given the key. See [how Agent Proxy works](/docs/claude-tag/concepts/agent-identity#agent-proxy).
4040
claude-tag/admins/connections/custom Changed · +28 / -28 lines
from line 22
2222
2323### Fill out the Custom tool form
2424
25| Field | What to enter |
26| :--------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
27| **Name** | A label for this connection (for example "Internal billing API") |
28| **Credential type** | Pick the type that matches how the API authenticates; see [Credential types](#credential-types) |
29| **Allowed websites** | The API's host (for example `api.example.com`). A wildcard is allowed as the leftmost label. You can't enter `*` alone here; a credential is always limited to specific hosts (see [Allow all hosts](/docs/claude-tag/admins/add-connections#allow-all-hosts)). The credential is sent only to hosts you list here. |
30| **Path prefixes** (optional) | Restrict the credential to specific URL paths under the host. Shown only for the MCP Connector type, and only when the provider you pick doesn't fix its own hosts and paths. |
31| **Custom headers** | Any extra headers the API requires beyond the credential. Shown only for the Bearer credential type. |
25| Field | What to enter |
26| :- | :- |
27| **Name** | A label for this connection (for example "Internal billing API") |
28| **Credential type** | Pick the type that matches how the API authenticates; see [Credential types](#credential-types) |
29| **Allowed websites** | The API's host (for example `api.example.com`). A wildcard is allowed as the leftmost label. You can't enter `*` alone here; a credential is always limited to specific hosts (see [Allow all hosts](/docs/claude-tag/admins/add-connections#allow-all-hosts)). The credential is sent only to hosts you list here. |
30| **Path prefixes** (optional) | Restrict the credential to specific URL paths under the host. Shown only for the MCP Connector type, and only when the provider you pick doesn't fix its own hosts and paths. |
31| **Custom headers** | Any extra headers the API requires beyond the credential. Shown only for the Bearer credential type. |
3232
3333After saving, where the credential has an allow rule, you can narrow it by HTTP method and path from its **Edit connection** dialog; see [Restrict by path or method](/docs/claude-tag/admins/add-connections#restrict-by-path-or-method).
3434
3535### Credential types
3636
37| Type | Use for |
38| :---------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
39| **Bearer** | An API key or token sent as `Authorization: Bearer <token>`. Most SaaS REST APIs. |
40| **Basic** | HTTP Basic authentication (`Authorization: Basic <base64(user:password)>`) |
41| **Body parameter** | A token the API expects in the request body or query string instead of a header |
42| **AWS SigV4** | AWS service APIs on `amazonaws.com` endpoints that require Signature Version 4 signing |
43| **GCP access token (with Service Account Key)** | Google Cloud APIs; the proxy exchanges the SA key for an access token |
44| **GCP IAP (with Service Account Key)** | Google Cloud services behind Identity-Aware Proxy |
45| **OAuth 2.0 JWT bearer** | APIs that accept a JWT signed with your private key in exchange for an access token (DocuSign, for example) |
46| **OAuth 2.0 client credentials** | Machine-to-machine OAuth with a client ID and secret |
47| **MCP Connector** | OAuth sign-in to one of the providers in the picker or to a [remote MCP connector](/docs/connectors/custom/add-unlisted) your organization has added on claude.ai. Sign in once as an admin; the agent acts as that account. Other OAuth APIs can't be connected this way. |
37| Type | Use for |
38| :- | :- |
39| **Bearer** | An API key or token sent as `Authorization: Bearer <token>`. Most SaaS REST APIs. |
40| **Basic** | HTTP Basic authentication (`Authorization: Basic <base64(user:password)>`) |
41| **Body parameter** | A token the API expects in the request body or query string instead of a header |
42| **AWS SigV4** | AWS service APIs on `amazonaws.com` endpoints that require Signature Version 4 signing |
43| **GCP access token (with Service Account Key)** | Google Cloud APIs; the proxy exchanges the SA key for an access token |
44| **GCP IAP (with Service Account Key)** | Google Cloud services behind Identity-Aware Proxy |
45| **OAuth 2.0 JWT bearer** | APIs that accept a JWT signed with your private key in exchange for an access token (DocuSign, for example) |
46| **OAuth 2.0 client credentials** | Machine-to-machine OAuth with a client ID and secret |
47| **MCP Connector** | OAuth sign-in to one of the providers in the picker or to a [remote MCP connector](/docs/connectors/custom/add-unlisted) your organization has added on claude.ai. Sign in once as an admin; the agent acts as that account. Other OAuth APIs can't be connected this way. |
4848
4949<Note>The **MCP Connector** type signs in to a connector from your organization's connector library. If you register a new connector from this form with **Add custom connector…**, that connector is added to the library on the **Connectors** page at [`claude.ai/admin-settings/connectors`](https://claude.ai/admin-settings/connectors), not only to the bundle. Removing the connection from the bundle later leaves the library entry in place.</Note>
5050
from line 65
6565
6666Requests to other hostnames fail before reaching AWS. Agent Proxy can't sign a request to a hostname with no region for any other service, such as `ec2.amazonaws.com`, or to a hostname with the region before the service name, such as an OpenSearch domain endpoint (`my-domain.us-east-1.es.amazonaws.com`). It also can't sign requests to an API Gateway custom domain or to a non-AWS API that uses Signature Version 4.
6767
68| Field | Value |
69| :---------------- | :---------------------------------------------------------------------------------------------------------- |
70| Access key ID | The IAM user or role access key, for example `AKIAIOSFODNN7EXAMPLE` |
71| Secret access key | The matching secret access key |
72| Session token | Optional. Only needed for temporary credentials from AWS STS. |
73| Allowed websites | The AWS service endpoint host, for example `s3.us-east-1.amazonaws.com` or `lambda.us-east-1.amazonaws.com` |
68| Field | Value |
69| :- | :- |
70| Access key ID | The IAM user or role access key, for example `AKIAIOSFODNN7EXAMPLE` |
71| Secret access key | The matching secret access key |
72| Session token | Optional. Only needed for temporary credentials from AWS STS. |
73| Allowed websites | The AWS service endpoint host, for example `s3.us-east-1.amazonaws.com` or `lambda.us-east-1.amazonaws.com` |
7474
7575Use long-lived credentials from a dedicated IAM user where you can. Temporary STS credentials work but expire on their own schedule, and the connection stops working when they do; you re-enter all three values to rotate.
7676
from line 80
8080
8181A `SignatureDoesNotMatch` response from AWS means the request AWS received doesn't match the one Agent Proxy signed.
8282
83| Check | What to do |
84| :---------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
85| The access key ID and secret access key belong to the same IAM identity | Re-enter the access key ID, secret access key, and session token together. The form is write-only, so a partial update can leave them mismatched. |
86| No proxy or gateway of your own sits between Anthropic and AWS | A second proxy that adds, strips, or reorders headers, or that re-signs the request, invalidates the signature Agent Proxy attached. Point **Allowed websites** at the AWS endpoint directly. |
83| Check | What to do |
84| :- | :- |
85| The access key ID and secret access key belong to the same IAM identity | Re-enter the access key ID, secret access key, and session token together. The form is write-only, so a partial update can leave them mismatched. |
86| No proxy or gateway of your own sits between Anthropic and AWS | A second proxy that adds, strips, or reorders headers, or that re-signs the request, invalidates the signature Agent Proxy attached. Point **Allowed websites** at the AWS endpoint directly. |
8787
8888A dropped or expired session token is a different failure: AWS rejects it with a token error such as `InvalidClientTokenId`, not `SignatureDoesNotMatch`. Rotate all three fields.
8989
claude-tag/admins/connections/datadog Changed · +9 / -9 lines
from line 22
2222
2323In the bundle, click **Connect** next to Datadog. The picker has three Datadog entries, one per site. Pick the one that matches your Datadog account's site.
2424
25| Picker entry | Site |
26| :---------------- | :------------------------------------------ |
27| **Datadog** | US1 (`api.datadoghq.com`), the default site |
28| **Datadog (US5)** | US5 (`api.us5.datadoghq.com`) |
29| **Datadog (EU)** | EU (`api.datadoghq.eu`) |
25| Picker entry | Site |
26| :- | :- |
27| **Datadog** | US1 (`api.datadoghq.com`), the default site |
28| **Datadog (US5)** | US5 (`api.us5.datadoghq.com`) |
29| **Datadog (EU)** | EU (`api.datadoghq.eu`) |
3030
3131The form asks for the same fields in all three.
3232
33| Field | Value |
34| :----------------------- | :------------------------------------------------------------------------------------------------------------------ |
35| Claude's API key | The API key from Datadog |
33| Field | Value |
34| :- | :- |
35| Claude's API key | The API key from Datadog |
3636| Claude's application key | The Application key from Datadog. Optional in the form; add it so Claude can read metrics, monitors, and dashboards |
37| Allowed websites | Prefilled by the preset; override for other sites (see below) |
37| Allowed websites | Prefilled by the preset; override for other sites (see below) |
3838
3939Datadog has a separate API host per site, and a key only works against its own. If your account is on a site without a picker entry, pick any Datadog entry and override the **Allowed websites** field with your site's API host: `api.us3.datadoghq.com`, `api.ap1.datadoghq.com`, or `api.ddog-gov.com`. To change the host later, open the **⋮** menu on this connection in the bundle's Credentials tab and choose **Edit**.
4040
claude-tag/admins/connections/gitlab Changed · +10 / -10 lines
from line 28
2828
2929**You'll see:** GitLab listed in the bundle's connections, and `@Claude what can you access from this channel?` returns it in a new thread under the bundle's scope. New threads pick up the connection on their own; in an existing thread, ask Claude to use the service by name.
3030
31| Field | Value |
32| :----------------------------- | :--------------------------------------------------------------------------------------------------------------- |
33| Claude’s personal access token | The token from GitLab, starting with `glpat-`. Project and group access tokens work here too. |
34| Allowed websites | `gitlab.com` (preset). For self-managed GitLab, open the **Advanced** tab and add your instance's hostname here. |
31| Field | Value |
32| :- | :- |
33| Claude’s personal access token | The token from GitLab, starting with `glpat-`. Project and group access tokens work here too. |
34| Allowed websites | `gitlab.com` (preset). For self-managed GitLab, open the **Advanced** tab and add your instance's hostname here. |
3535
3636GitLab's own guide for creating tokens is at [docs.gitlab.com](https://docs.gitlab.com/api/rest/authentication/).
3737
3838## How GitLab differs from GitHub
3939
40| | GitLab | GitHub |
41| :-------------------------------- | :------------------------------------------------------------ | :---------------------------------------------------------------------------------------------------- |
42| Auth | A service account's personal access token | The Claude GitHub App, [installed separately](/docs/claude-tag/admins/configure-github) |
43| Referencing a project in a thread | Give Claude the full project URL; it reads it through the API | Typing `owner/repo` in the message auto-attaches it |
44| Self-managed | Your hostname under **Advanced → Allowed websites** | [GitHub Enterprise setup](/docs/claude-tag/admins/configure-github#github-enterprise) |
45| Handing back changes | Manages issues and comments on merge requests through the API | [Draft pull requests](/docs/claude-tag/users/use-cases/work-with-github) authored by the Claude GitHub App |
40| | GitLab | GitHub |
41| :- | :- | :- |
42| Auth | A service account's personal access token | The Claude GitHub App, [installed separately](/docs/claude-tag/admins/configure-github) |
43| Referencing a project in a thread | Give Claude the full project URL; it reads it through the API | Typing `owner/repo` in the message auto-attaches it |
44| Self-managed | Your hostname under **Advanced → Allowed websites** | [GitHub Enterprise setup](/docs/claude-tag/admins/configure-github#github-enterprise) |
45| Handing back changes | Manages issues and comments on merge requests through the API | [Draft pull requests](/docs/claude-tag/users/use-cases/work-with-github) authored by the Claude GitHub App |
4646
4747The connection is API-only. The token authenticates GitLab API requests, not git, so Claude gets a 401 error when it tries to clone a private project or push to any project over HTTPS, even with the connection in place. To clone a repository into the session workspace, connect it through [GitHub](/docs/claude-tag/admins/configure-github) instead.
4848