One read of Claude Documentationclaude-docs-20261020T163706Z
9 pages moved out of 277 read.
Pages moved
9
significant first
Pages read
277
in this capture
Captured
16:37 UTC
Corpus hash
e3e6841625ef
corpus-hash
What this read moved
1-9 of 9government/changelog Changed · +8 / -0 lines
from line 2
22
33> Release notes for Claude for Government
44
5<Update label="Claude Code 2.1.302" description="2026-10-16">
6 * Changed unattended runs of the Claude Code command-line tool, such as `claude -p`, where **Auto mode** is set to **Allowed**: on Claude Code 2.1.302 or later they start in Auto mode only when Auto mode is chosen for them.
7</Update>
8
9<Update label="Claude Code 2.1.299" description="2026-10-14">
10 * Changed **Managed hooks** on Windows devices without Git for Windows: on Claude Code 2.1.299 or later, a managed hook written as a Bash command that checks a tool call or a permission request blocks that action when the command fails.
11</Update>
12
513<Update label="2026.10.01.1">
614 * Added a **New members start here** option to self-managed seat tiers, so you can pick the tier new members start on.
715</Update>
government/config/settings Changed · +8 / -6 lines
from line 171
171171
172172The **Claude Code** section of the **Config** page holds your organization's settings for Claude Code. Claude for Government delivers them to the command-line tool after a member signs in, and in Claude Desktop 2.9939.2 or later they can also reach Code sessions. While Claude Code is in [early access](/docs/government/deploy-claude-code/configure), the section appears once your agency has access.
173173
174* **Blocked shell commands**: command names, such as `curl` or `ssh`, that Claude Code never runs. None are blocked by default.
174* **Blocked shell commands**: command names, such as `curl` or `ssh`, that Claude Code never runs with its Bash and PowerShell tools. None are blocked by default.
175175* **Managed hooks**: hooks that run in every member's Claude Code sessions, such as a command that writes an audit record after each tool use. None are set by default.
176176* **Member-added hooks**: whether hooks and custom status lines that members set up in their own or their projects' settings run as well. **Blocked** by default. Managed hooks still run, and in Claude Desktop so do hooks inside plugins.
177177* **Plugin sources**: where members can install Claude Code plugins from, one of **None**, **Approved sources only** with an **Approved plugin sources** list, or **Any source** with a **Blocked plugin sources** list. **None** by default. The two switches under [Member-added plugins and marketplaces](#member-added-plugins-and-marketplaces) narrow **Any source**. While **Let members add plugin marketplaces** is off, members install only from the **Approved plugin sources** list. While **Let members add their own plugins** is off, they cannot add a source of their own from a file or folder on their machine.
from line 201
201201
202202### Let members add their own connectors
203203
204Controls whether members can add connectors of their own in Claude Desktop, as local MCP servers under **Settings**, then **Developer**. The **Let members add their own connectors** switch is off by default. It sets Claude Desktop's [`isLocalDevMcpEnabled`](/docs/third-party/claude-desktop/configuration#islocaldevmcpenabled) key.
204Controls whether members can add connectors of their own in Claude Desktop, as local MCP servers under **Settings**, then **Developer**. The **Let members add their own connectors** switch is off by default. It sets Claude Desktop's [`isLocalDevMcpEnabled`](/docs/third-party/claude-desktop/configuration#islocaldevmcpenabled) key. While the switch is off, Claude Desktop ignores connectors that members already added under **Developer**.
205205
206206### Let members create skills
207207
from line 243
243243
244244## Tool and connector cards
245245
246Alongside the settings list, the Config page shows cards for the built-in tools (Web search, Web fetch, and Shell commands), the built-in connector (Microsoft 365), a **Connectors** card for the ones you add yourself, and a **Plugins** card for plugin packages you upload. A connector is an integration that lets Claude reach an external service on a user's behalf.
246Alongside the settings list, the Config page shows cards for the built-in tools (Web search, Web fetch, Shell commands, and Terminal panel tools), the built-in connector (Microsoft 365), a **Connectors** card for the ones you add yourself, and a **Plugins** card for plugin packages you upload. A connector is an integration that lets Claude reach an external service on a user's behalf.
247247
248248The **Web search** card controls whether Claude can search the web in Claude Desktop. It is off by default. When you turn it on you are shown a short description of how search works and asked to acknowledge it before the setting is saved. A **Require approval for each search** sub-setting sits below the toggle and becomes available once web search is on; it is on by default, and turning it off lets each member choose whether to approve every search or allow searches to run automatically.
249249
250250Once you turn web search on, each member's Claude Desktop picks it up the next time the app starts and shows it in the message box's **+** menu, under **Connectors**, as a **Web Search** switch that the member can turn off for themselves. If one member has no **Web Search** switch after restarting Claude Desktop while others do, select [**Compare config across levels**](/docs/government/config/overview#comparing-settings-across-levels) at the top of the Config page and type the member's name into the search box to check whether another level, such as a [directory group](/docs/government/config/overview#group-specific-settings), turns web search off for them. If every level shows web search on, check whether that member's network is blocking it, as described in the troubleshooting table in [Connect Claude Desktop to Claude for Government](/docs/government/deploy-desktop/configure#troubleshooting).
251251
252The **Web fetch** card controls whether Claude can fetch web pages in Claude Desktop. It is on by default, and fetches are subject to the Allowed network hosts list above. A **Require approval for each fetch** sub-setting sits below the toggle. Turning it on asks the member to approve every page fetch before it runs; when it is off (the default), each member chooses whether to approve fetches or allow them automatically.
252The **Web fetch** card controls whether Claude can fetch web pages in Claude Desktop. It is on by default, and fetches are subject to the Allowed network hosts list above. A **Require approval for each fetch** sub-setting sits below the toggle. Turning it on asks the member to approve every page fetch before it runs; when it is off (the default), fetches in Chat and Cowork run without asking, and Code sessions follow [Claude Code's usual permission rules](https://code.claude.com/docs/en/permissions).
253253
254The **Shell commands** card controls whether Claude can run shell commands during tasks in Claude Desktop. It is on by default, and turning it off also turns off Advanced file analysis in Chat. A **Require approval for each command** sub-setting sits below the toggle. Turning it on asks the member to approve every shell command before it runs; when it is off (the default), each member chooses whether to approve commands or allow them automatically. On Claude Desktop versions earlier than 2.110.0, Chat asks before each command regardless of this setting.
254The **Shell commands** card controls whether Claude can run shell commands during tasks in Claude Desktop. It is on by default, and turning it off also turns off Advanced file analysis in Chat. A **Require approval for each command** sub-setting sits below the toggle. Turning it on asks the member to approve every shell command before it runs; when it is off (the default), Cowork runs sandbox commands without asking, as does Chat on Claude Desktop 2.110.0 or later, and Code sessions follow [Claude Code's usual permission rules](/docs/government/security/security-and-data-handling#code-in-claude-desktop). On Claude Desktop versions earlier than 2.110.0, Chat asks before each command regardless of this setting.
255
256The **Terminal panel tools** card controls whether Claude can run commands in the Code tab's Terminal panel in Claude Desktop, and open, list, or stop its tabs. It is on by default, and turning off the **Shell commands** card turns these tools off as well. See [Code in Claude Desktop](/docs/government/security/security-and-data-handling#code-in-claude-desktop) for how those commands run.
255257
256258The **Microsoft 365** card lets members reach your agency's Microsoft 365 content, including SharePoint, OneDrive, Outlook, and Teams, from Claude Desktop. Each member signs in with their own Microsoft account. Enter the **Tenant ID** and **Client ID** from an application you register in Microsoft Entra, choose the **Azure cloud** your Microsoft tenant is in, and select which Microsoft Graph permissions to allow under **Access**. The connector is off while Tenant ID and Client ID are both blank. See [Set up the Microsoft 365 connector](/docs/government/connectors/microsoft-365) for the full walkthrough.
257259
government/deploy-claude-code/configure Changed · +11 / -13 lines
from line 17
1717* **Claude Code is current.** This setup requires Claude Code 2.1.267 or later (`claude --version`).
1818* **Claude Desktop is current.** Update Claude Desktop to [the supported version](/docs/government/deploy-desktop/configure#before-you-begin) before turning on Claude Code for the terminal.
1919* **Devices can reach Claude for Government.** Claude Code must reach the gateway address over HTTPS on port 443, and the user's browser must reach the Claude for Government host, its sign-in service, and your agency's identity provider, the same hosts that [Claude Desktop sign-in](/docs/government/deploy-desktop/configure#before-you-begin) needs.
20* **You can place a system-level file or policy.** The settings are enforced only from a system-level location: a file in a system directory, a macOS configuration profile, or a machine-level Windows registry policy. Deliver them through your device management system or by hand with administrator rights.
20* **You can place a system-level file or policy.** The settings are enforced only from a system-level location: a file in a system directory, a macOS configuration profile, or a machine-level Windows registry policy. Values for the same keys in a user's own settings cannot override them. Deliver them through your device management system or by hand with administrator rights.
2121
2222## The managed settings
2323
from line 35
3535```json theme={null}
3636{
3737 "forceLoginMethod": "gateway",
38 "forceLoginGatewayUrl": "https://<claude-for-government-gateway-address>",
38 "forceLoginGatewayUrl": "https://<claude-for-government-host>/gateway-api",
3939 "env": {
4040 "CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": "1",
4141 "DISABLE_TELEMETRY": "1",
from line 50
5050}
5151```
5252
53Your Anthropic representative provides the gateway address. Replace `<claude-for-government-gateway-address>` with it so the value is the full address starting with a single `https://`, including any path. The address is the same for every device and contains no credentials, so one file serves your whole fleet.
53For an agency that reaches Claude for Government on a hostname of its own, your Anthropic representative provides the address, which replaces the whole value. Otherwise, replace `<claude-for-government-host>` with the domain name you use to access Claude for Government, the host in your Claude Desktop [`bootstrapUrl`](/docs/government/deploy-desktop/configure#the-managed-setting). The address contains no credentials.
5454
55Claude Code requires the gateway sign-in only when the two sign-in keys come from a system-level location. Set there, they take the place of the same keys in a user's own settings file; a value in a per-user registry policy does not turn the sign-in on.
56
5755### Before sign-in
5856
5957Your organization's settings reach Claude Code only after a user has signed in. Until then, the first four variables keep Claude Code's release-notes download, update checks, automatic setup of the official plugin marketplace, and usage telemetry and error reporting to Anthropic off from the first launch. After sign-in the organization's settings keep them off.
from line 80
8280Windows Registry Editor Version 5.00
8381
8482[HKEY_LOCAL_MACHINE\SOFTWARE\Policies\ClaudeCode]
85; substitute the Claude for Government gateway address
86"Settings"="{\"forceLoginMethod\":\"gateway\",\"forceLoginGatewayUrl\":\"https://<claude-for-government-gateway-address>\",\"env\":{\"CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC\":\"1\",\"DISABLE_TELEMETRY\":\"1\",\"DISABLE_ERROR_REPORTING\":\"1\",\"CLAUDE_CODE_DISABLE_OFFICIAL_MARKETPLACE_AUTOINSTALL\":\"1\",\"ANTHROPIC_CUSTOM_HEADERS\":\"\",\"CLAUDE_CODE_EXTRA_BODY\":\"\",\"NODE_TLS_REJECT_UNAUTHORIZED\":\"1\",\"NODE_EXTRA_CA_CERTS\":\"\"},\"parentSettingsBehavior\":\"merge\"}"
83; substitute your Claude for Government host
84"Settings"="{\"forceLoginMethod\":\"gateway\",\"forceLoginGatewayUrl\":\"https://<claude-for-government-host>/gateway-api\",\"env\":{\"CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC\":\"1\",\"DISABLE_TELEMETRY\":\"1\",\"DISABLE_ERROR_REPORTING\":\"1\",\"CLAUDE_CODE_DISABLE_OFFICIAL_MARKETPLACE_AUTOINSTALL\":\"1\",\"ANTHROPIC_CUSTOM_HEADERS\":\"\",\"CLAUDE_CODE_EXTRA_BODY\":\"\",\"NODE_TLS_REJECT_UNAUTHORIZED\":\"1\",\"NODE_EXTRA_CA_CERTS\":\"\"},\"parentSettingsBehavior\":\"merge\"}"
8785```
8886
8987A value under `HKEY_CURRENT_USER` does not turn on gateway sign-in.
from line 106
108106 </Step>
109107
110108 <Step title="Confirm the gateway certificate">
111 The first time each user connects from a device, Claude Code shows the first 16 characters of the gateway's TLS certificate fingerprint (SHA-256) and asks them to trust it. Publish the expected fingerprint to your users with the rollout (they compare it ignoring colons and letter case), and again when Anthropic renews the certificate, because users are asked again after a renewal. Your Anthropic representative provides it.
109 The first time each user connects from a device, Claude Code shows the first 16 characters of the gateway's TLS certificate fingerprint (SHA-256) and asks them to trust it. Publish the expected fingerprint to your users with the rollout (they compare it ignoring colons and letter case), and again when the certificate is renewed, because users are asked again after a renewal. Your Anthropic representative provides it.
112110 </Step>
113111
114112 <Step title="Finish sign-in in the browser">
from line 118
120118 </Step>
121119</Steps>
122120
123A sign-in lasts until the organization's [Session idle timeout](/docs/government/config/settings#session-idle-timeout) or [Maximum session length](/docs/government/config/settings#maximum-session-length) is reached, and at most 30 days. It also ends when the user's account is deactivated, or when the user signs in to Claude Code on more devices than Claude for Government allows at once (six), which ends the sign-in closest to expiring (see [Sessions](/docs/government/account/sessions#how-long-sessions-last)). Claude Code then asks the user to sign in again, which they do with `/login`.
121A sign-in lasts until the organization's [Session idle timeout](/docs/government/config/settings#session-idle-timeout) or [Maximum session length](/docs/government/config/settings#maximum-session-length) is reached, and at most 30 days. It also ends when the user's account is deactivated, when an administrator signs the user out, or when the user signs in to Claude Code on more devices than Claude for Government allows at once (six), which ends the sign-in closest to expiring (see [Sessions](/docs/government/account/sessions#how-long-sessions-last)). Claude Code then asks the user to sign in again, which they do with `/login`.
124122
125123## Confirm it worked
126124
from line 148
150148| - | - | - |
151149| Claude Code offers claude.ai and Claude Console sign-in instead of the **Cloud gateway** screen | The managed settings did not reach Claude Code: wrong path, a Windows value under `HKEY_CURRENT_USER` or with another name, a misspelled key, or Claude Code was already running | Check the location for the operating system above, then quit and restart Claude Code |
152150| The **Cloud gateway** screen says to contact your IT administrator | `forceLoginGatewayUrl` is missing or empty | Add the gateway address to the same managed settings and restart Claude Code |
153| Claude Code reports that it could not resolve the gateway host, or another connection error for the address shown | The address in `forceLoginGatewayUrl` is not exactly the one your Anthropic representative provided, or the device cannot reach it | Correct the address, or restore the device's route to the gateway over HTTPS on port 443, then restart Claude Code |
151| Claude Code reports that it could not resolve the gateway host, or another connection error for the address shown | The address in `forceLoginGatewayUrl` is not exactly the gateway address described under [The managed settings](#the-managed-settings), or the device cannot reach it | Correct the address, or restore the device's route to the gateway over HTTPS on port 443, then restart Claude Code |
154152| `Unable to connect to Anthropic services` at first start, before any sign-in screen | The sign-in keys did not reach Claude Code from a system-level location, or Claude Code is out of date | Update Claude Code, or check the settings location, then start it again |
155153| `claude doctor`, run before sign-in on the standard installer, reports auto-updates as enabled | The `env` block did not reach Claude Code | Compare the deployed settings with the sample above, then restart Claude Code |
156154| When it starts or right after sign-in, Claude Code exits with `Cloud gateway <address> refused managed settings for this account (403): Claude Code may not be enabled for your organization` | The **Claude Code** switch is off at a level that applies to the user (tenant, organization, or directory group) | Turn on the **Claude Code** switch under [Product availability](/docs/government/config/settings#product-availability) at that level (at the tenant level, **Reset to default** instead lets each organization's own switch decide), then have the user start Claude Code again. [**Compare config across levels**](/docs/government/config/overview#comparing-settings-across-levels) on the **Config** page shows which level turns it off for a user |
157155| When it starts or right after sign-in, Claude Code exits with `Couldn't load settings from Cloud gateway <address>` | Claude Code could not reach the gateway while loading the organization's settings | Confirm the device reaches the gateway over HTTPS on port 443, then have the user start Claude Code again. If it persists on a connected device, contact your Anthropic representative |
158| In a session that was working, every request fails with a 403 error saying the product is not available for the organization | The **Claude Code** switch was turned off while Claude Code was running | Turn the switch back on at the level that turned it off; the next request then succeeds |
156| In a session that was working, every request fails with a 403 error saying Claude Code is not turned on for the organization | The **Claude Code** switch was turned off while Claude Code was running | Turn the switch back on at the level that turned it off; the next request then succeeds |
159157| Before the user has signed in, Claude Code exits with `Administrator policy requires a Cloud gateway sign-in on this machine` | A credential from earlier use is present: `ANTHROPIC_API_KEY` or `ANTHROPIC_AUTH_TOKEN` in the environment, an `apiKeyHelper` in the user's settings, or a saved Claude Console key | Remove the variable or the `apiKeyHelper` entry, or have the user run `claude auth logout`, then start `claude` and sign in |
160158| Claude Code says the gateway's TLS certificate changed and asks the user to run `/login` | The gateway certificate was renewed | Confirm the new fingerprint with your Anthropic representative, send it to users, and have them run `/login` and accept it |
161159
162160## Things to know
163161
164* Only the gateway sign-in described on this page delivers the organization's settings to the Claude Code command-line tool. Once a user is signed in, those settings replace the Claude Code policy in these managed settings, hooks and permission rules included, apart from the two sign-in keys, any `env` variables the organization's settings leave unset, and the [keys Claude Code reads from every admin source](https://code.claude.com/docs/en/managed-settings#keys-read-from-every-admin-source).
162* Only a gateway sign-in delivers the organization's settings to the Claude Code command-line tool. Once a user is signed in, those settings replace the Claude Code policy in these managed settings, hooks and permission rules included, apart from the two sign-in keys, any `env` variables the organization's settings leave unset, and the [keys Claude Code reads from every admin source](https://code.claude.com/docs/en/managed-settings#keys-read-from-every-admin-source).
165163* A claude.ai sign-in left on a device from earlier use is ignored once these settings are in place. A leftover `ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`, `apiKeyHelper`, or saved Claude Console key is not: until the user has signed in through the gateway, Claude Code stops and asks for its removal, as [Troubleshooting](#troubleshooting) describes.
164* A cloud provider selected earlier in a user's environment or Claude Code settings, such as Amazon Bedrock, still applies whenever Claude Code has no gateway sign-in for the user, for example before the first sign-in or after one expires: Claude Code then uses that provider instead of requiring the gateway sign-in. Remove that provider selection from devices you set up for Claude for Government.
166165* Where the Claude Code extension for VS Code is used, have users remove an earlier claude.ai sign-in with `claude auth logout` or the extension's **Claude Code: Logout** command before they sign in through the gateway, not after: both commands clear every credential Claude Code has stored, the gateway sign-in included.
167166* To take a device out of this setup, have its users sign out with `claude auth logout` before you remove the settings.
168167* After sign-in, the organization's settings turn off the Claude Code settings that run a helper command (`apiKeyHelper`, `proxyAuthHelper`, `awsAuthRefresh`, `awsCredentialExport`, `gcpAuthRefresh`, `otelHeadersHelper`), wherever it is set. If your devices reach the network through a proxy that needs a helper command to authenticate, raise this with your Anthropic representative before you deploy.
169* Claude Code connects to Claude for Government through a user's [sign-in](#sign-in) rather than an API key or service account. A CI pipeline or other unattended run therefore works only on a device where a user has signed in, until that sign-in ends.
170168* With Claude for Government, the command-line tool has no access to Claude Code features that [require a claude.ai account](https://code.claude.com/docs/en/feature-availability#features-that-require-a-claude-subscription), such as cloud sessions, Remote Control, and routines. [Fast mode](https://code.claude.com/docs/en/fast-mode) isn't available either.
171169* With these settings Claude Code does not check for or install updates in the background. Distribute new versions through your software deployment tooling, or have users run `claude update` (standard installer) or their package manager.
172170* Code sessions inside Claude Desktop sign in through Claude Desktop, not through these settings, but the `env` block applies to them too. For the other settings that govern them on a device that also has these managed settings, see [Code in Claude Desktop](/docs/government/security/security-and-data-handling#code-in-claude-desktop).
government/org-admin/compliance-api Changed · +3 / -3 lines
from line 47
4747
4848The exclusive bounds `created_at.gt` and `created_at.lt` are also accepted if your collector needs them.
4949
50The API serves the most recent 30 days of activity. A lower bound earlier than that is treated as 30 days ago.
51
5052### Response format
5153
5254The response is a JSON envelope containing a page of events and the cursors for the next and previous pages.
from line 117
115117}
116118```
117119
118The top-level `user_id` and `user_email` fields appear on activities recorded after they were added to the API. Earlier activities are not updated, so your collector should treat these fields as optional.
119
120120### Activity types
121121
122122Event types use a dotted `resource.action` naming convention. The categories emitted today include:
from line 132
132132
133133## Connecting to your SIEM
134134
135Most deployments run a small scheduled worker that polls the API on a fixed interval, forwards each event to the SIEM's HTTP ingest endpoint, and records a time watermark so the next run picks up where the last one left off.
135Most deployments run a small scheduled worker that polls the API on a fixed interval, forwards each event to the SIEM's HTTP ingest endpoint, and records a time watermark so the next run picks up where the last one left off. A worker that falls more than 30 days behind cannot recover the gap.
136136
137137A typical run requests `since=<watermark>`, forwards every event returned, and if `has_more` is true, follows `after_id=<last_id>` for each further page until `has_more` is false. After all pages are drained, advance your watermark to the newest `created_at` you saw. Event `id` values are stable and unique, so your collector can deduplicate on `id` and safely retry a page or use an overlapping `since` without creating duplicate records in the SIEM.
138138
government/security/security-and-data-handling Changed · +10 / -4 lines
from line 38
3838
3939On macOS and Linux, those shell commands run inside an operating-system-level sandbox that the application builds from your organization's **Allowed network hosts** and **Allowed workspace folders** settings on the [Config](/docs/government/config/settings#allowed-network-hosts) page. The sandbox is in place whenever either setting restricts access, which the default configuration does. Inside the sandbox, a command can create or change files only in the session's folder, the other folders **Allowed workspace folders** permits, and temporary locations. Unless [**Block reads outside workspace folders**](/docs/government/config/settings#block-reads-outside-workspace-folders) is on, it can read any file on the device that the user's account can open. By default it runs without asking the user first. A user can exempt specific commands from this sandbox in a Claude Code settings file, and an exempted command runs outside the sandbox under the permission mode the user selects for the session.
4040
41Claude can also type commands into the Code tab's terminal, which is the user's own shell (PowerShell on Windows). The app asks the user to approve each of those commands by default, and they run as the user, outside any sandbox. Administrators can turn these terminal tools off with the **Terminal panel tools** card on the [Config](/docs/government/config/settings#tool-and-connector-cards) page. The [**Blocked shell commands**](/docs/government/config/settings#claude-code) list does not block commands Claude types into the terminal, but the **Require approval for each command** sub-setting on the **Shell commands** card applies to them in every permission mode.
42
4143On Linux, the sandbox requires the `bubblewrap` and `socat` packages, so install both on each workstation as described under [Set up Linux and WSL2](https://code.claude.com/docs/en/sandboxing#set-up-linux-and-wsl2) in the Claude Code documentation. If either package is missing, shell commands run outside the sandbox as they do on Windows.
4244
4345On macOS and Linux, the sandbox also blocks connections to local Unix sockets. A command that talks to a local agent through a socket, such as git signing a commit with a key held in an SSH agent or a hardware-backed key manager, cannot reach that agent from inside the sandbox. On macOS, a user who needs such a command to work can list the agent's socket path under `sandbox.network.allowUnixSockets` in their Claude Code settings file, which keeps the command inside the sandbox. Every sandboxed command in that user's Code sessions can then ask the agent to sign or authenticate, so this is appropriate only for an agent that asks the user to approve each use, for example with Touch ID, and not for an agent that signs without prompting.
from line 115
113115 </Accordion>
114116
115117 <Accordion title="Can individual shell commands be allowlisted enterprise-wide?">
116 Not in Chat or Cowork. Administrators can turn the built-in **Web search**, **Web fetch**, and **Shell commands** tools on or off, or require approval on every use, but cannot allowlist individual commands within those tools. In Chat, an approval for a shell command covers that one command, with no standing approval. For analyses that take many steps, Cowork runs shell commands in the sandbox without prompting; you make Cowork available to members under **Product availability** on the [Config](/docs/government/config/settings#product-availability) page. In Code sessions, the [Claude Code](/docs/government/config/settings#claude-code) section has no setting that allows individual commands. Permission rules in a Claude Code managed-settings file on the device can allow individual commands, but they apply in Code sessions only where your organization's Claude Code settings don't reach them, as [Code in Claude Desktop](#code-in-claude-desktop) describes.
118 Not in Chat or Cowork. Administrators can turn the built-in **Web search**, **Web fetch**, and **Shell commands** tools on or off, or require approval on every use, but cannot allowlist individual commands within those tools. In Chat, an approval for a shell command covers that one command, with no standing approval. For analyses that take many steps, Cowork runs shell commands in the sandbox without prompting; you make Cowork available to members under **Product availability** on the [Config](/docs/government/config/settings#product-availability) page. In Code sessions, the [Claude Code](/docs/government/config/settings#claude-code) section has no list of allowed commands. Permission rules in a Claude Code managed-settings file on the device can allow individual commands, but they apply in Code sessions only where your organization's Claude Code settings don't reach them, as [Code in Claude Desktop](#code-in-claude-desktop) describes.
117119 </Accordion>
118120
119121 <Accordion title="Can users suppress approval prompts with an Always allow choice?">
from line 125
123125
124126### Connectors
125127
126In Claude for Government, connectors fall into three main categories: built-in tools (Web search, Web fetch, and Shell commands), the built-in Microsoft 365 connector, and connectors an administrator adds on the Connectors card of the [Config](/docs/government/config/settings#tool-and-connector-cards) page.
128In Claude for Government, connectors fall into three main categories: built-in tools (Web search, Web fetch, Shell commands, and Terminal panel tools), the built-in Microsoft 365 connector, and connectors an administrator adds on the Connectors card of the [Config](/docs/government/config/settings#tool-and-connector-cards) page.
127129
128130<AccordionGroup>
129131 <Accordion title="Where do connectors run, and where are tokens stored?">
130 Connectors are called from the desktop application, outside the sandbox. The built-in Microsoft 365 connector and administrator-added connectors call their endpoints directly from the user's device, through the system proxy where one is configured. OAuth tokens for both are stored encrypted on each user's device using operating system encryption (macOS Keychain on Mac, DPAPI on Windows). For administrator-added connectors, the bearer header entered on the Config page is delivered to each user's desktop. A plugin package can include skills, slash commands, sub-agents, and hooks, which run on the member's machine. The Config page asks the administrator to confirm trust before adding a plugin that declares components that can run code on the member's machine, for example hooks or an MCP server. When an administrator adds a plugin on the Config page, Claude Desktop can run a local MCP server that the plugin declares on the member's machine, or connect to a remote one. The **Let members add their own connectors** switch on the Config page controls whether end users can add local MCP servers of their own in Claude Desktop, under **Settings**, then **Developer**. It is off by default, as described under [Let members add their own connectors](/docs/government/config/settings#let-members-add-their-own-connectors). The **Let members add plugin marketplaces** and **Let members add their own plugins** switches on the Config page control whether end users can add plugin marketplaces or plugins of their own in Claude Desktop. Both are off by default, as described under [Member-added plugins and marketplaces](/docs/government/config/settings#member-added-plugins-and-marketplaces). A user-added plugin's skills, slash commands, sub-agents, and hooks run on that user's machine, and any connector it declares does not become available as an organization connector. Administrators distribute plugins to members on the Config page with a per-plugin choice of automatic installation or member opt-in. See [Connectors](/docs/government/connectors/overview) and the Plugins card under [Tool and connector cards](/docs/government/config/settings#tool-and-connector-cards).
132 Connectors are called from the desktop application, outside the sandbox. The built-in Microsoft 365 connector and administrator-added connectors call their endpoints directly from the user's device, through the system proxy where one is configured. OAuth tokens for both are stored encrypted on each user's device using operating system encryption (macOS Keychain on Mac, DPAPI on Windows). For administrator-added connectors, the bearer header entered on the Config page is delivered to each user's desktop.
133
134 A plugin package can include skills, slash commands, sub-agents, and hooks, which run on the member's machine. The Config page asks the administrator to confirm trust before adding a plugin that declares components that can run code on the member's machine, for example hooks or an MCP server. When an administrator adds a plugin on the Config page, Claude Desktop can run a local MCP server that the plugin declares on the member's machine, or connect to a remote one. Administrators distribute plugins to members on the Config page with a per-plugin choice of automatic installation or member opt-in. The **Let members add their own connectors** switch on the Config page controls whether end users can add local MCP servers of their own in Claude Desktop, under **Settings**, then **Developer**. It is off by default, as described under [Let members add their own connectors](/docs/government/config/settings#let-members-add-their-own-connectors). The **Let members add plugin marketplaces** and **Let members add their own plugins** switches on the Config page control whether end users can add plugin marketplaces or plugins of their own in Claude Desktop. Both are off by default, as described under [Member-added plugins and marketplaces](/docs/government/config/settings#member-added-plugins-and-marketplaces).
135
136 A user-added plugin's skills, slash commands, sub-agents, and hooks run on that user's machine, and any connector it declares does not become available as an organization connector. Hook commands and local MCP servers run as programs under the user's own account, outside both the [sandbox virtual machine](#sandbox-and-isolation) and the [Code session sandbox](#code-in-claude-desktop). See [Connectors](/docs/government/connectors/overview) and the Plugins card under [Tool and connector cards](/docs/government/config/settings#tool-and-connector-cards).
131137 </Accordion>
132138
133139 <Accordion title="Do connectors follow the sandbox egress allowlist?">
from line 233
227233
228234<AccordionGroup>
229235 <Accordion title="Which domains does Claude Code need to reach?">
230 The Claude for Government gateway address that your Anthropic representative provides, over HTTPS on port 443, for sign-in, organization settings, and model inference. Sign-in finishes in the user's browser, which needs the Claude for Government host, its sign-in service, and your agency's identity provider, as for Claude Desktop. Claude Code also reaches, from the user's device, the address of each connector an administrator applies to **Claude Code** on the **Connectors** card, and that connector's sign-in service when it uses OAuth. The managed settings from [Connect Claude Code to Claude for Government](/docs/government/deploy-claude-code/configure#before-sign-in) turn off Claude Code's background connections before sign-in (release notes, update checks, and the official plugin marketplace).
236 The Claude for Government gateway address in the managed settings from [Connect Claude Code to Claude for Government](/docs/government/deploy-claude-code/configure#the-managed-settings), over HTTPS on port 443, for sign-in, organization settings, and model inference. Sign-in finishes in the user's browser, which needs the Claude for Government host, its sign-in service, and your agency's identity provider, as for Claude Desktop. Claude Code also reaches, from the user's device, the address of each connector an administrator applies to **Claude Code** on the **Connectors** card, and that connector's sign-in service when it uses OAuth. The managed settings from [Connect Claude Code to Claude for Government](/docs/government/deploy-claude-code/configure#before-sign-in) turn off Claude Code's background connections before sign-in (release notes, update checks, and the official plugin marketplace).
231237 </Accordion>
232238
233239 <Accordion title="Does Claude Code send telemetry to Anthropic?">
third-party/claude-desktop/import Changed · +27 / -1 lines
## Make an imported project folder readable in Chat
from line 143
143143 <img src="https://mintcdn.com/claude-ai/HpR2FaaZXZXkiUcV/images/third-party/import/import-trust-resume.png?fit=max&auto=format&n=HpR2FaaZXZXkiUcV&q=85&s=806d0d2018d7fc0f10afb71035b1f807" alt="An imported conversation open in Cowork with a yellow Resume imported session card offering Go back and Trust and resume buttons." width="1800" height="688" data-path="images/third-party/import/import-trust-resume.png" />
144144</Frame>
145145
146## Make an imported project folder readable in Chat
147
148When an import brings over a project, it puts a folder on the project. In Chat, Claude can't read that folder until you add it to the project again. Add the folder once for each imported project.
149
150<Steps>
151 <Step title="Open the project">
152 Go to the **Projects** page and open the imported project.
153 </Step>
154
155 <Step title="Note the folder path">
156 Next to **Context**, click **+**, then select **Choose a folder**. Under **Recent**, find the project's folder, which is dimmed and can't be selected, and note the path shown under its name.
157 </Step>
158
159 <Step title="Add the folder again">
160 Select **Choose a different folder**. In the folder dialog, go to the path you noted and select the project's folder.
161 </Step>
162
163 <Step title="Start a new conversation">
164 Start a new conversation in the project. In the new conversation, Claude can read the files in the folder.
165 </Step>
166</Steps>
167
168Importing the project again doesn't make its folder readable. If you remove the import under **Import history** in **Settings > Import & export**, or archive the project, and then import from claude.ai again, the new project uses the same folder. Add the folder to the new project again.
169
170Your administrator can also limit which folders Claude reads. See [Project folders in Chat](/docs/third-party/claude-desktop/chat#project-folders-in-chat).
171
146172## Export sessions to move them to another device
147173
148174When your administrator also sets `exportEnabled` to `true` under `claudeAiImport`, **Settings → Import & export** offers **Export…**, which writes this computer's chats, Cowork tasks, and Code sessions (not terminal Claude Code sessions) to a zip file. On the other device, open the import wizard and select that zip with **Choose file…**; the wizard lists its sessions in the [Cowork & Code step](#step-2-local-cowork-and-code-sessions). The export is a one-time snapshot, not a sync, and the zip contains full conversation content, so handle it as sensitive data.
from line 178
152178## What is and isn't included
153179
154180* **Your data only.** An export contains your own conversations, projects, and memory. Other workspace members' content is not included.
155* **Chats and projects come over.** Each imported project appears on the **Projects** page. If the project has custom instructions, Claude Desktop shows them in the project for you to review and accept before they take effect. In Chat, Claude can't read a folder that the import put on a project until you add the folder to the project again and start a new conversation. See [Project folders in Chat](/docs/third-party/claude-desktop/chat#project-folders-in-chat).
181* **Chats and projects come over.** Each imported project appears on the **Projects** page. If the project has custom instructions, Claude Desktop shows them in the project for you to review and accept before they take effect. In Chat, Claude can't read a folder that the import put on a project until you [add the folder to the project again](#make-an-imported-project-folder-readable-in-chat).
156182* **Artifacts come over as files.** For artifacts Claude created in a conversation, and files Claude wrote with its file-creation tool, the import saves the final version as one of the imported conversation's output files. Earlier versions aren't kept. Past a size limit, the rest of a conversation's artifact content isn't imported, and the conversation says so.
157183* **Project knowledge files and conversation attachments do not.** A member's own export never includes the contents of files uploaded to a project's knowledge or attached to a conversation. This is a security policy on claude.ai, and it applies to both the **Sign in to claude.ai** and **Choose a downloaded file** paths. Imported chats keep the messages that referenced an attachment, but not the file itself. The only export that includes file contents is an organization-level export, which only a workspace owner can request.
158184* **One-time copy.** Imported history does not stay in sync with claude.ai. Run the import again to pick up newer conversations; existing imports are matched and skipped, so you won't get duplicates.
government/desktop/plugins Changed · +1 / -1 lines
from line 58
5858
5959## What plugins add in Claude for Government
6060
61A plugin adds its skills, slash commands, sub-agents, and hooks, and its hooks run on your machine at defined points during a session. The connectors your administrators provide appear under **Customize**, then **Connectors**. Connectors declared by a plugin you add yourself are not added to Claude Desktop's connectors.
61A plugin adds its skills, slash commands, sub-agents, and hooks, and its hooks run on your machine at defined points during a session. The connectors your administrators provide appear under **Customize**, then **Connectors**. A plugin can also declare connectors of its own. Whether they connect depends on the settings your administrators choose.
6262
third-party/claude-desktop/chat Changed · +1 / -1 lines
from line 31
3131
3232For a conversation inside a project, Claude can list and read files in folders added to the project in Claude Desktop, and can't change them.
3333
34* **Folders the user adds.** To have Claude read a folder, the user adds it to the project in Claude Desktop and starts a new conversation. For a folder that an [import](/docs/third-party/claude-desktop/import) put on the project, or that was on the project before Chat could read folders, the user adds it to the project again.
34* **Folders the user adds.** To have Claude read a folder, the user adds it to the project in Claude Desktop and starts a new conversation. For a folder that an [import](/docs/third-party/claude-desktop/import) put on the project, or that was on the project before Chat could read folders, the user adds it to the project again. For the steps, see [Make an imported project folder readable in Chat](/docs/third-party/claude-desktop/import#make-an-imported-project-folder-readable-in-chat).
3535* **Folders you allow.** If you set [`allowedWorkspaceFolders`](/docs/third-party/claude-desktop/configuration#allowedworkspacefolders), the list also limits which of a project's folders Claude reads.
3636
3737## What a Chat conversation cannot do
third-party/claude-desktop/code Changed · +1 / -1 lines
from line 76
7676With `"merge"`, two Claude Code policy keys weaken `blockReadsOutsideWorkingDirectories`. `sandbox.filesystem.allowManagedReadPathsOnly` limits the block to Claude's file tools, so a shell command that reads outside the working directories asks for approval instead of failing, and `allowManagedPermissionRulesOnly` removes the session's read access to its plugin and attachment folders, so skills that read their own files stop working. Leave both out of your Claude Code policy if you rely on the block.
7777
7878<Note>
79 In a third-party deployment there is no Anthropic authentication, so Claude Code's server-managed settings tier is never present. If you have not separately deployed a Claude Code `managed-settings.json` or OS profile, Claude Desktop's policy applies automatically and you do not need to set `parentSettingsBehavior`.
79 If you have not separately deployed a Claude Code `managed-settings.json` or OS profile, Claude Desktop's policy applies automatically and you do not need to set `parentSettingsBehavior`.
8080</Note>
8181
8282## Claude Code mods