Follow Discord
Sweep 22 Sep 2026 · 17:19Z Build v2.1.280 501 read Stable v2.1.267 Latest v2.1.280 Next v2.1.280 Feeds RSS JSON llms.txt Unofficial
One capture · claude-docs

One read of Claude Documentation

11 pages moved out of 234 read.

claude-docs-20260915T180704Z

Pages moved 11 significant first
Pages read 234 in this capture
Captured 18:07 UTC
Corpus hash 26ca168b7617 corpus-hash

What this read moved

1–11 of 11

government/config/settings Changed · +11 / -1 lines

### Restart deadline for configuration changes ### Member-added plugins and marketplaces

from line 1
11# Available settings
22 
3> Reference for the product settings on the Config page in Claude for Government, including session timeout, maximum session length, organization instructions, telemetry, automatic updates, Claude Desktop banner, product availability, and the tool and connector cards.
3> Reference for the product settings on the Config page in Claude for Government, including session timeout, maximum session length, organization instructions, telemetry, automatic updates, Claude Desktop banner, product availability, member-added plugins, and the tool and connector cards.
44 
55> **Who this is for:** Tenant administrators and organization owners who set product behavior for the people they manage.
66 
from line 116
116116 Members who are running Claude Desktop when you change **Block automatic updates** or **Restart deadline for updates** may need to restart the app to pick up the change.
117117</Note>
118118 
119### Restart deadline for configuration changes
120 
121How long a member can put off restarting Claude Desktop after the app detects a configuration change, as a whole number of hours from 0 to 336 (14 days). When the deadline passes, the app shows a restart dialog that the member cannot dismiss, and restarts on its own once the member has been inactive for 2 minutes and Claude has no task in progress. A value of 0 requires the restart as soon as the app detects the change. Leave the value empty to allow 24 hours.
122 
119123### Claude Desktop banner
120124 
121125A persistent banner shown at the top of Claude Desktop. You can set the text, colors, and an optional link, and preview the result as you edit. Banner text may be up to 200 characters, leading and trailing spaces are rejected, colors must be valid hex codes, and the link (if set) must begin with `https://`. An empty banner is valid and simply hides it.
from line 141
137141<Note>
138142 This layout applies to Claude Desktop 1.26832.0 and later. Earlier versions show **Chat**, **Cowork**, and **Code** as three separate tabs, controlled by the same switches.
139143</Note>
144 
145### Member-added plugins and marketplaces
146 
147Two switches that control whether members can add plugins of their own in Claude Desktop. **Let members add plugin marketplaces** lets members add plugin marketplaces and install plugins from them. **Let members add their own plugins** lets members upload plugin files or have Claude create a plugin for them. Both switches are off by default.
148 
149While a switch is off, Claude Desktop hides the corresponding controls from members. Marketplaces and plugins that members added earlier keep working, and members can still install plugins from those marketplaces.
140150 
141151### Allowed network hosts
142152 

government/deploy-desktop/configure Changed · +12 / -12 lines

from line 29
2929* **The device meets Claude Desktop's requirements.** See the Claude Desktop [system requirements](/docs/third-party/claude-desktop/installation#system-requirements) for macOS and Windows device requirements. For a Windows fleet, work through the [Windows fleet checklist](/docs/government/deploy-desktop/windows-checklist), which covers the Virtual Machine Platform feature that Cowork needs along with the installer, policy, and network prerequisites.
3030* **Windows devices used for Code have Git for Windows.** On Windows, only the Code part of Claude Desktop needs Git for Windows. Chat and Cowork work without it. Install Git on the devices whose users will work in Code, or turn **Code in Claude Desktop** off under [Product availability](/docs/government/config/settings#product-availability) so that users are not prompted to install Git.
3131* **You can install the app.** Installing by hand needs administrator rights on each device; see [Configure a single machine](#configure-a-single-machine) for what that means on each platform. Installing through your device management system does not, because the management system installs with elevated rights. The [macOS deployment guide](https://support.claude.com/en/articles/12611117-deploy-claude-desktop-for-macos) and the [Windows deployment guide](https://support.claude.com/en/articles/12622703-deploy-claude-desktop-for-windows) cover where to download the installer and how to distribute it.
32* **The app is current.** The configuration mechanism on this page requires Claude Desktop 1.10628.0 or later.
32* **The app is current.** Deploy Claude Desktop 1.46388.1 or later.
3333 
3434## The managed setting
3535 
from line 57
5757 
5858The configuration that the app downloads for a user includes the following settings, all of which you manage in this portal.
5959 
60| What the app receives | Where it is set |
61| ---------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
62| Which of Chat, Cowork, and Code the user can open, and whether Advanced file analysis is on in Chat | [Product availability](/docs/government/config/settings#product-availability) on the Config page |
63| The models the user can choose | The user's [seat tier](/docs/government/org-admin/seat-tiers) |
64| Connectors, plugins, and the settings for the built-in tools | The [tool and connector cards](/docs/government/config/settings#tool-and-connector-cards) on the Config page |
65| The hosts that tools may reach | [Allowed network hosts](/docs/government/config/settings#allowed-network-hosts) |
66| The folders a user can choose as a workspace | [Allowed workspace folders](/docs/government/config/settings#allowed-workspace-folders) |
67| The banner shown across the top of the app | [Claude Desktop banner](/docs/government/config/settings#claude-desktop-banner) |
68| Where the app sends your agency's own telemetry, if you have set a collector | [Telemetry endpoint](/docs/government/config/settings#telemetry-endpoint) |
69| Whether automatic updates are blocked, and the restart deadline for an update the app has downloaded | [Block automatic updates](/docs/government/config/settings#block-automatic-updates) and [Restart deadline for updates](/docs/government/config/settings#restart-deadline-for-updates) on the Config page |
60| What the app receives | Where it is set |
61| ----------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
62| Which of Chat, Cowork, and Code the user can open, and whether Advanced file analysis is on in Chat | [Product availability](/docs/government/config/settings#product-availability) on the Config page |
63| The models the user can choose | The user's [seat tier](/docs/government/org-admin/seat-tiers) |
64| Connectors, plugins, and the settings for the built-in tools | The [tool and connector cards](/docs/government/config/settings#tool-and-connector-cards) on the Config page |
65| The hosts that tools may reach | [Allowed network hosts](/docs/government/config/settings#allowed-network-hosts) |
66| The folders a user can choose as a workspace | [Allowed workspace folders](/docs/government/config/settings#allowed-workspace-folders) |
67| The banner shown across the top of the app | [Claude Desktop banner](/docs/government/config/settings#claude-desktop-banner) |
68| Where the app sends your agency's own telemetry, if you have set a collector | [Telemetry endpoint](/docs/government/config/settings#telemetry-endpoint) |
69| Whether automatic updates are blocked, and the restart deadlines for a downloaded update and for a configuration change | [Block automatic updates](/docs/government/config/settings#block-automatic-updates), [Restart deadline for updates](/docs/government/config/settings#restart-deadline-for-updates), and [Restart deadline for configuration changes](/docs/government/config/settings#restart-deadline-for-configuration-changes) on the Config page |
7070 
7171## Configure a single machine
7272 
from line 167
167167If you later move a test device's values to `HKEY_LOCAL_MACHINE`, move all of them, because once any value exists under `HKLM\SOFTWARE\Policies\Claude` the app ignores `HKEY_CURRENT_USER` entirely.
168168 
169169<Note>
170 Cowork, the agentic workspace in Claude Desktop, requires the **Virtual Machine Platform** Windows optional feature. Enable that feature through your device management system before rollout. On a device where the feature is not enabled, Cowork is unavailable until someone turns the feature on, which requires administrator rights that a standard user does not have. Chat works regardless of this feature. The [Windows fleet checklist](/docs/government/deploy-desktop/windows-checklist) lists the remaining Windows prerequisites.
170 Cowork, the agentic workspace in Claude Desktop, requires the **Virtual Machine Platform** Windows optional feature. Enable that feature through your device management system before rollout. On a device where the feature is not enabled, Cowork is unavailable until someone turns the feature on, which requires administrator rights that a standard user does not have. Chat works without this feature, except for Advanced file analysis. The [Windows fleet checklist](/docs/government/deploy-desktop/windows-checklist) lists the remaining Windows prerequisites and explains what to do [if some devices are not ready for Cowork](/docs/government/deploy-desktop/windows-checklist#if-some-devices-are-not-ready-for-cowork).
171171</Note>
172172 
173173### Linux

government/deploy-desktop/windows-checklist Changed · +4 / -0 lines

### If some devices are not ready for Cowork

from line 47
4747 
4848On a device that does not meet these requirements, Chat still works apart from Advanced file analysis, and Cowork reports that it is unavailable. If a device meets them and Cowork still fails to start, check whether endpoint security software is blocking the agent helper, as described under [Application control rules](#application-control-rules).
4949 
50### If some devices are not ready for Cowork
51 
52You can deploy Claude Desktop to devices that do not yet meet the [Cowork virtualization](#cowork-virtualization) requirements. Before you deploy to those devices, have a tenant administrator or organization owner turn off the **Cowork in Claude Desktop** and **Advanced file analysis in Chat** switches under [Product availability](/docs/government/config/settings#product-availability) for the devices' users, for example through a [directory group](/docs/government/config/overview#group-specific-settings) that contains them. With both switches off, those users keep Chat and Code, and the app does not download or start the virtual machine on their devices. Turn both switches back on once those devices meet the requirements.
53 
5054## Configuration values
5155 
5256* **Two registry values.** Push the two values described under [Windows](/docs/government/deploy-desktop/configure#windows) as machine policy under `HKLM\SOFTWARE\Policies\Claude`: the required `bootstrapUrl` and the recommended `disableDeploymentModeChooser`. No other values are needed to connect the app, because everything else reaches each user from Claude for Government at sign-in. If your agency distributes Claude Desktop updates itself, also add the value described under [Automatic updates](/docs/government/deploy-desktop/configure#automatic-updates).

government/desktop/plugins Changed · +7 / -6 lines

from line 8
88 
99## Where plugins come from
1010 
11In Claude for Government, plugins reach you in four ways:
11In Claude for Government, plugins reach you in three ways:
1212 
1313* Your administrators add plugins for your organization, and some of them install automatically.
14* You upload a plugin file you have.
15* You ask Claude to create a plugin with you.
16* You add a plugin marketplace and install plugins from it.
14* If your administrators let you add your own plugins, you can upload a plugin file or ask Claude to create a plugin with you.
15* If your administrators let you add plugin marketplaces, you can add a marketplace and install plugins from it.
1716 
18Claude for Government does not include a public plugin marketplace; your administrators add your organization's plugins. You can also add a plugin marketplace of your own from **Browse plugins**. Your deployment's network controls determine whether a marketplace can be downloaded.
17Claude for Government does not include a public plugin marketplace; your administrators add your organization's plugins. Your deployment's network controls determine whether a marketplace you add can be downloaded.
1918 
2019## Find and install plugins
2120 
from line 22
2322 
2423A plugin your administrators set to install automatically is already installed. A plugin they offer for you to choose stays available on the **Organization** tab until you install it.
2524 
26To install a plugin from a file, select **Add plugin**, then **Upload plugin**, and choose the plugin's `.zip` file. Claude Desktop shows a notice reminding you to install only plugins you trust, since uploaded plugins are not controlled by Anthropic. To have Claude build one, select **Add plugin**, then **Create with Claude**, and describe the plugin you want. Claude builds it for you, and you install the result.
25If your administrators let you add your own plugins, you can install a plugin from a file or have Claude build one. To install from a file, select **Add**, then **Upload plugin**, and choose the plugin's `.zip` file. Claude Desktop shows a notice reminding you to install only plugins you trust, since uploaded plugins are not controlled by Anthropic. To have Claude build one, select **Add**, then **Create with Claude**, and describe the plugin you want. Claude builds it for you, and you install the result.
26 
27If your administrators let you add plugin marketplaces, you can add a marketplace of your own. To add one, select **Browse**, then select the **+** button (**Add marketplace**) at the top right of the **Directory** that opens.
2728 
2829## Manage installed plugins
2930 

third-party/claude-desktop/configuration Changed · +6 / -5 lines

from line 286
286286 
287287 **Extended context** (`supports1m`) is a capability assertion you make about your deployment; only set it for models you've confirmed support the 1M-token window:
288288 
289 ```json theme={null}
289 ```json theme={null} theme={null} theme={null} theme={null} theme={null}
290290 [{"name": "claude-sonnet-5", "supports1m": true}, "claude-opus-4-8"]
291291 ```
292292 
from line 294
294294 
295295 **Display label** (`labelOverride`) is for IDs the picker can't derive a friendly name from (Bedrock ARNs, gateway routing aliases). Display-only; `name` is still what the app sends:
296296 
297 ```json theme={null}
297 ```json theme={null} theme={null} theme={null} theme={null} theme={null}
298298 [{"name": "arn:aws:bedrock:us-east-1:123:application-inference-profile/abc", "labelOverride": "Claude Opus (Prod)"}]
299299 ```
300300 
301301 **Tier mapping** (`anthropicFamilyTier`) tells the app which Claude tier (`haiku`/`sonnet`/`opus`/`fable`/`mythos`) an entry stands in for, so bare tier aliases (e.g. in Code sessions) resolve to your model. `isFamilyDefault: true` picks the winner when several entries share a tier:
302302 
303 ```json theme={null}
303 ```json theme={null} theme={null} theme={null} theme={null} theme={null}
304304 [{"name": "us.anthropic.claude-opus-4-8", "anthropicFamilyTier": "opus"}]
305305 ```
306306 
from line 334
334334 <Accordion title="inferenceModelPricing details">
335335 Each row replaces Anthropic list price for one model in the Usage page's estimate, in USD per million tokens (`inputPerMtok`, `outputPerMtok`, `cacheReadPerMtok`, `cacheWritePerMtok`, all four required; `cacheWritePerMtok` prices both 5-minute and 1-hour cache writes); rows apply only while `inferenceModelPricingEnabled` is `true` and do not turn the estimate on by themselves. Mirrors Claude Code's managed `modelPricing.overrides`, and `name` is matched the same way: a built-in Claude model ID (e.g. `claude-sonnet-4-6`, or its Bedrock, Vertex, or Foundry ID) covers every dated and provider spelling of that model; any other value (a gateway alias, an inference-profile ARN) matches that exact ID only (case-insensitive) and wins over a built-in row. An ID Claude Code cannot map to a Claude model at all gets no estimate until a row here prices it. `inferenceModelPricingMultiplier` still applies on top of a row.
336336 
337 ```json theme={null}
337 ```json theme={null} theme={null} theme={null} theme={null} theme={null}
338338 {"inferenceModelPricingEnabled": true, "inferenceModelPricingMultiplier": 0.9, "inferenceModelPricing": [{"name": "claude-sonnet-4-6", "inputPerMtok": 2.4, "outputPerMtok": 12, "cacheReadPerMtok": 0.24, "cacheWritePerMtok": 3}]}
339339 ```
340340 
from line 954
954954 <Accordion title="orgPluginSettings details">
955955 Locks per-tool permissions on MCP servers provided by any installed plugin — from the org-plugins directory or a plugin marketplace, remote or run locally — one entry per server name (compared case-insensitively):
956956 
957 ```json theme={null}
957 ```json theme={null} theme={null} theme={null} theme={null} theme={null}
958958 [{"serverName": "internal-search", "tools": [{"toolName": "delete_document", "permission": "blocked"}]}]
959959 ```
960960 
from line 1070
10701070 | [`disableNonessentialTelemetry`](#disablenonessentialtelemetry) | `true` |
10711071 | [`disableNonessentialServices`](#disablenonessentialservices) | `true` |
10721072 | [`disableAutoUpdates`](#disableautoupdates) | `true` |
1073 | [`modelCatalogEnabled`](#modelcatalogenabled) | `false` |
10731074 | [`isLocalDevMcpEnabled`](#islocaldevmcpenabled) | `false` |
10741075 | [`isDesktopExtensionEnabled`](#isdesktopextensionenabled) | `false` |
10751076 | [`skillCreationEnabled`](#skillcreationenabled) | `false` |

third-party/claude-desktop/telemetry Changed · +4 / -4 lines

from line 144
144144| `downloads.claude.ai` | VM workspace bundle and Claude CLI binary, fetched at session start |
145145| `downloads.claude.ai` | Claude Code model catalog (signed picker metadata), polled every 5–15 minutes |
146146 
147Without this host reachable, Chat conversations, Cowork tasks, and Code sessions cannot start on a device that has not yet downloaded these components. App updates often change one or both of these components, and the app then downloads the new versions from the same host. Devices installed with the [offline installer variant](/docs/third-party/claude-desktop/installation#offline-installation), which includes both components in the installer package, are not affected.
147Without this host reachable, Chat conversations, Cowork tasks, and Code sessions cannot start on a device that has not yet downloaded these components. App updates often change one or both of these components, and the app then downloads the new versions from the same host. Devices installed with the [offline installer variant](/docs/third-party/claude-desktop/installation#offline-installation), which includes both components in the installer package, are not affected. The model catalog fetch is not needed to run the app: set [`modelCatalogEnabled`](/docs/third-party/claude-desktop/configuration#modelcatalogenabled) to `false` to turn it off, or [`modelCatalogUrl`](/docs/third-party/claude-desktop/configuration#modelcatalogurl) to fetch the catalog from a mirror inside your network. While the catalog is unreachable, sessions still start and the model picker keeps the names and effort options the app last fetched or shipped with.
148148 
149149### Inference provider
150150 
from line 267
267267 
268268## Disabling all Anthropic-bound connections
269269 
270With `disableEssentialTelemetry`, `disableNonessentialTelemetry`, `disableNonessentialServices`, and `disableAutoUpdates` all set to `true`, the desktop application makes **no outbound connections to Anthropic-operated hosts at runtime**. If Code sessions can use Web Fetch, also set [`skipWebFetchPreflight`](/docs/third-party/claude-desktop/configuration#skipwebfetchpreflight) to `true` (or add `WebFetch` to `disabledBuiltinTools`), because Claude Code in [Code](/docs/third-party/claude-desktop/code) sessions otherwise checks each fetched domain with `api.anthropic.com`. The only required egress is `downloads.claude.ai` (for the VM workspace bundle and Claude CLI binary at session start) and your inference provider. With the [offline installer variant](/docs/third-party/claude-desktop/installation#offline-installation), `downloads.claude.ai` is not needed either, and your inference provider is the only required egress. Enabling [SSH remote sessions](/docs/third-party/claude-desktop/ssh-remote-sessions) adds `downloads.claude.ai` back, except on devices installed with the offline installer that connect only to Linux x64 or arm64 hosts: that installer bundles the remote-session components for those hosts, and connections to hosts on other platforms still download them. Enabling [import from claude.ai](/docs/third-party/claude-desktop/import) likewise lets the app reach `claude.ai` and `api.anthropic.com` (and `storage.googleapis.com` for the export download), but only while a user runs a sign-in import from the wizard.
270With `disableEssentialTelemetry`, `disableNonessentialTelemetry`, `disableNonessentialServices`, and `disableAutoUpdates` all set to `true`, and [`modelCatalogEnabled`](/docs/third-party/claude-desktop/configuration#modelcatalogenabled) set to `false`, the desktop application makes **no outbound connections to Anthropic-operated hosts at runtime**. Without `modelCatalogEnabled: false`, the app also fetches the signed model catalog from `downloads.claude.ai` at launch and then every 5 to 15 minutes, regardless of the four telemetry and update keys, and on devices installed with the offline installer too. A blocked catalog request affects nothing else, and the model picker keeps the names and effort options the app last fetched or shipped with. To keep the catalog without reaching `downloads.claude.ai`, set [`modelCatalogUrl`](/docs/third-party/claude-desktop/configuration#modelcatalogurl) to a mirror inside your network. If Code sessions can use Web Fetch, also set [`skipWebFetchPreflight`](/docs/third-party/claude-desktop/configuration#skipwebfetchpreflight) to `true` (or add `WebFetch` to `disabledBuiltinTools`), because Claude Code in [Code](/docs/third-party/claude-desktop/code) sessions otherwise checks each fetched domain with `api.anthropic.com`. The only required egress is `downloads.claude.ai` (for the VM workspace bundle and Claude CLI binary at session start) and your inference provider. With the [offline installer variant](/docs/third-party/claude-desktop/installation#offline-installation), `downloads.claude.ai` is not needed either, and your inference provider is the only required egress. Enabling [SSH remote sessions](/docs/third-party/claude-desktop/ssh-remote-sessions) adds `downloads.claude.ai` back, except on devices installed with the offline installer that connect only to Linux x64 or arm64 hosts: that installer bundles the remote-session components for those hosts, and connections to hosts on other platforms still download them. Enabling [import from claude.ai](/docs/third-party/claude-desktop/import) likewise lets the app reach `claude.ai` and `api.anthropic.com` (and `storage.googleapis.com` for the export download), but only while a user runs a sign-in import from the wizard.
271271 
272An app that receives its configuration from the [Enterprise Admin Console](/docs/third-party/claude-desktop/admin-console) still connects to Anthropic with all four of these keys set to `true`. The app contacts `api.anthropic.com` at every launch and at each configuration check (every 10 minutes by default) to download its configuration. The app contacts `claude.ai` when the user signs in. While the organization's **Report desktop usage to this organization** switch is on, the app also sends [usage analytics](/docs/third-party/claude-desktop/admin-console#usage-analytics) counts to `api.anthropic.com` every few minutes during use. You turn the telemetry categories for these apps on and off on the console's **Telemetry & updates** page.
272An app that receives its configuration from the [Enterprise Admin Console](/docs/third-party/claude-desktop/admin-console) still connects to Anthropic with all of these keys set. It never fetches the model catalog (its model names and options come from the console's settings), and it contacts `api.anthropic.com` at every launch and at each configuration check (every 10 minutes by default) to download its configuration. The app contacts `claude.ai` when the user signs in. While the organization's **Report desktop usage to this organization** switch is on, the app also sends [usage analytics](/docs/third-party/claude-desktop/admin-console#usage-analytics) counts to `api.anthropic.com` every few minutes during use. You turn the telemetry categories for these apps on and off on the console's **Telemetry & updates** page.
273273 
274274These settings control only the application's telemetry, update, and non-essential service connections. They do not change how your inference provider handles conversation content at the endpoint. On Microsoft Foundry, the Claude models behind your inference endpoint run in an Anthropic-operated service, so conversation content reaches Anthropic-operated infrastructure regardless of these settings. See [Data handling by provider](/docs/third-party/claude-desktop/overview#data-handling-by-provider) on the Overview page.
275275 

government/config/plugins-and-connectors Changed · +1 / -1 lines

from line 50
5050 
5151You do not need to push anything for a plugin to reach members. Claude Desktop syncs your organization's plugin list when it starts and periodically while it runs, so an auto-installed plugin appears on its own, and a member who already has the application open receives it at the next sync. A member can remove a plugin you installed automatically, and it stays removed on the device where they removed it.
5252 
53In Claude Desktop, members can also add plugins of their own, by uploading a plugin file or having Claude create one, as described in [Plugins in Claude Desktop](/docs/government/desktop/plugins). Those plugins are separate from the ones you add and do not appear on the **Plugins** card.
53Two switches, **Let members add plugin marketplaces** and **Let members add their own plugins**, control whether members can also add plugins of their own in Claude Desktop, as described under [Member-added plugins and marketplaces](/docs/government/config/settings#member-added-plugins-and-marketplaces). Both are off by default. Plugins that members add are separate from the ones you add and do not appear on the **Plugins** card.
5454 
5555## Where plugins are added
5656 

government/security/security-and-data-handling Changed · +1 / -1 lines

from line 124
124124 
125125<AccordionGroup>
126126 <Accordion title="Where do connectors run, and where are tokens stored?">
127 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. End users cannot add their own connectors. End users can upload their own plugin files in Claude Desktop; a user-uploaded plugin's skills, 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).
127 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. End users cannot 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).
128128 </Accordion>
129129 
130130 <Accordion title="Do connectors follow the sandbox egress allowlist?">

third-party/claude-desktop/installation Changed · +1 / -1 lines

from line 151
151151 
152152Download the installer from a connected machine and bring it across your boundary with your usual software-distribution process.
153153 
154Pair the offline installer with [`disableAutoUpdates`](/docs/third-party/claude-desktop/configuration#disableautoupdates): the app cannot reach the update feed from an air-gapped network, and you update the fleet by distributing each new offline installer through your MDM. Aside from updates, the only egress an air-gapped deployment needs is your inference provider; see [Telemetry and egress](/docs/third-party/claude-desktop/telemetry#required-egress-paths).
154Pair the offline installer with [`disableAutoUpdates`](/docs/third-party/claude-desktop/configuration#disableautoupdates). The app cannot reach the update feed from an air-gapped network, and you update the fleet by distributing each new offline installer through your MDM. Also set [`modelCatalogEnabled`](/docs/third-party/claude-desktop/configuration#modelcatalogenabled) to `false`, or point [`modelCatalogUrl`](/docs/third-party/claude-desktop/configuration#modelcatalogurl) at a mirror inside your network. Otherwise the app tries to fetch the signed model catalog from `downloads.claude.ai` at launch and every 5 to 15 minutes after that, and while those requests fail the model picker keeps the names and effort options that ship with the app. With updates and the catalog fetch handled this way, the only egress an air-gapped deployment needs is your inference provider; see [Telemetry and egress](/docs/third-party/claude-desktop/telemetry#required-egress-paths).
155155 
156156## Updates
157157 

third-party/claude-desktop/mdm Changed · +1 / -1 lines

from line 90
9090The hosts the app needs to reach depend on the configuration you built: your inference provider's endpoint is always required, and each telemetry, update, and service setting you leave enabled adds its own hosts. The configuration window shows the exact allowlist for your settings and can export it as a text file for your network team.
9191 
9292<Warning>
93 `downloads.claude.ai` is required to run the app regardless of your configuration: it serves the VM workspace bundle and the latest Claude Code binary, fetched at session start. Without it, Chat conversations, Cowork tasks, and Code sessions cannot start on a device that has not yet downloaded these components. App updates often change one or both of these components, and the app then downloads the new versions from the same host. The [offline installer variant](/docs/third-party/claude-desktop/installation#offline-installation) builds both components into the installer package and does not need this host.
93 `downloads.claude.ai` is required to run the app regardless of your configuration: it serves the VM workspace bundle and the latest Claude Code binary, fetched at session start. Without it, Chat conversations, Cowork tasks, and Code sessions cannot start on a device that has not yet downloaded these components. App updates often change one or both of these components, and the app then downloads the new versions from the same host. The [offline installer variant](/docs/third-party/claude-desktop/installation#offline-installation) builds both components into the installer package and does not need this host. The app still requests the model catalog from `downloads.claude.ai` unless [`modelCatalogEnabled`](/docs/third-party/claude-desktop/configuration#modelcatalogenabled) is `false` or [`modelCatalogUrl`](/docs/third-party/claude-desktop/configuration#modelcatalogurl) names a mirror inside your network, and sessions start whether or not that request succeeds.
9494</Warning>
9595 
9696Open these hosts on your perimeter firewall before rolling out to devices. See [Telemetry and egress](/docs/third-party/claude-desktop/telemetry#required-egress-paths) for the full list of hosts grouped by the setting that controls each one, and for the distinction between the perimeter firewall and the in-app sandbox allowlist.

third-party/claude-desktop/overview Changed · +2 / -2 lines

from line 68
6868 
6969This section applies when using Google Cloud's Agent Platform or Amazon Bedrock.
7070 
71Because inference runs in your cloud tenant, Claude Desktop on 3P operates inside whatever compliance boundary your provider and region give you. The desktop application itself contacts Anthropic-operated hosts only to download the VM workspace bundle and Claude CLI binary (always required), and for crash reporting, product analytics, non-essential services (connector favicons, artifact previews, and MCP Apps widgets), and auto-updates. Each of the latter four can be disabled independently via managed configuration.
71Because inference runs in your cloud tenant, Claude Desktop on 3P operates inside whatever compliance boundary your provider and region give you. The desktop application itself contacts Anthropic-operated hosts only to download the VM workspace bundle and Claude CLI binary (always required), and for crash reporting, product analytics, non-essential services (connector favicons, artifact previews, and MCP Apps widgets), auto-updates, and the published model catalog that labels the model picker. Each of the latter five can be disabled independently via managed configuration.
7272 
73With Anthropic-bound telemetry, non-essential services, and updates all disabled, the only remaining Anthropic-operated egress is `downloads.claude.ai` for the VM workspace bundle and Claude CLI binary at session start. An app managed from the [Enterprise Admin Console](/docs/third-party/claude-desktop/admin-console) still contacts `api.anthropic.com` at launch and at each configuration re-check, and `claude.ai` at sign-in. If Code sessions can use Web Fetch, also set [`skipWebFetchPreflight`](/docs/third-party/claude-desktop/configuration#skipwebfetchpreflight) to `true` (or add `WebFetch` to `disabledBuiltinTools`), because Claude Code in [Code](/docs/third-party/claude-desktop/code) sessions otherwise checks each fetched domain with `api.anthropic.com`. Beyond that, the compliance posture of your deployment is determined by your inference provider. See [Telemetry and egress](/docs/third-party/claude-desktop/telemetry) for the full set of network paths and how to lock them down.
73With Anthropic-bound telemetry, non-essential services, updates, and the [model catalog fetch](/docs/third-party/claude-desktop/configuration#modelcatalogenabled) all disabled, the only remaining Anthropic-operated egress is `downloads.claude.ai` for the VM workspace bundle and Claude CLI binary at session start. An app managed from the [Enterprise Admin Console](/docs/third-party/claude-desktop/admin-console) still contacts `api.anthropic.com` at launch and at each configuration re-check, and `claude.ai` at sign-in. If Code sessions can use Web Fetch, also set [`skipWebFetchPreflight`](/docs/third-party/claude-desktop/configuration#skipwebfetchpreflight) to `true` (or add `WebFetch` to `disabledBuiltinTools`), because Claude Code in [Code](/docs/third-party/claude-desktop/code) sessions otherwise checks each fetched domain with `api.anthropic.com`. Beyond that, the compliance posture of your deployment is determined by your inference provider. See [Telemetry and egress](/docs/third-party/claude-desktop/telemetry) for the full set of network paths and how to lock them down.
7474 
7575## HIPAA
7676 
Feedback