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

4 pages moved out of 238 read.

claude-docs-20260917T170712Z

Pages moved 4 significant first
Pages read 238 in this capture
Captured 17:07 UTC
Corpus hash cc82af9f5885 corpus-hash

What this read moved

1–4 of 4

third-party/claude-desktop/browser New page · 81 lines, new page

# Built-in browser and Claude in Chrome ## Claude in Chrome ### Turn on Claude in Chrome ### Set up Claude in Chrome on a device ## Built-in browser ### Turn on the built-in browser ### Restrict which sites Claude can open ### Manage the built-in browser from the Enterprise Admin Console ## Site safety check ## Related

A whole new page. There's nothing to diff it against, so here is what it says.

# Built-in browser and Claude in Chrome

> Configuring Claude in Chrome and the built-in browser in Cowork and Code for Claude Desktop 3P

In Claude Desktop on third-party (3P), Claude can work with web pages in Cowork and Code sessions through Claude in Chrome or through the built-in browser. [Claude in Chrome](#claude-in-chrome) lets Claude work in the user's own Google Chrome or Microsoft Edge and is available to organizations managed from the [Enterprise Admin Console](/docs/third-party/claude-desktop/admin-console). The [built-in browser](#built-in-browser) is a pane inside Claude Desktop that any deployment can turn on with the [`builtinBrowserEnabled`](/docs/third-party/claude-desktop/configuration#builtinbrowserenabled) key, and three related keys control which sites Claude can open in it.

## Claude in Chrome

[Claude in Chrome](https://claude.com/chrome) is Anthropic's browser extension. It lets Claude work in the user's own Google Chrome or Microsoft Edge, with the tabs and sign-ins the user already has there. In Claude Desktop on 3P, it is available only to organizations managed from the [Enterprise Admin Console](/docs/third-party/claude-desktop/admin-console), because it relies on the work-account sign-in to Claude Desktop that only those organizations use. When the configuration comes from MDM, a local file, or a bootstrap server, use the [built-in browser](#built-in-browser) instead.

When Claude in Chrome is on, Claude can open and work in tabs in the user's browser during Cowork and Code sessions. Model requests still go to your inference provider.

### Turn on Claude in Chrome

In **Organization settings** on claude.ai, open the **Claude in Chrome** page and turn on the **Enable for your team** switch. On the same page, choose whether Claude in Chrome works on every site except the ones you block, or only on the sites you allow. Then add sites with the **Add websites** button. These site permissions are the same ones the built-in browser uses for your organization.

Claude in Chrome also needs the **Allow user-added MCP servers** switch on the **Connectors** page under **Desktop 3P** in **Organization settings** to stay on. While that switch is off, Claude Desktop doesn't connect to Claude in Chrome.

### Set up Claude in Chrome on a device

Users install [Claude in Chrome](https://claude.com/chrome) from the Chrome Web Store in Google Chrome or Microsoft Edge on macOS or Windows, or you deploy the extension to them with Chrome's management policies, as described under [Permissions required to install Claude in Chrome](https://support.claude.com/en/articles/12012173-get-started-with-claude-in-chrome). Each user signs in to the extension with the same work account they use in Claude Desktop. Claude Desktop then connects to the extension automatically, and Claude can use that browser in the user's Cowork and Code sessions.

## Built-in browser

When the built-in browser is on, Cowork and Code sessions show a **Browser** pane where users can open and sign in to any site. In the pane, Claude can open pages, read them, click, type, fill in forms, take screenshots, and run JavaScript on a page.

Before Claude acts on a site, Claude Desktop asks the user to approve it. **Allow once** covers that page, and **Always allow** saves the site on the device until the user revokes it in **Settings**. After a user approves a site, Claude can read and interact with its pages as the user sees them, including pages behind the user's sign-in on that site.

Pages load directly from the user's device, so your network's proxy, firewall, and DNS filtering apply to them. Sign-ins and cookies from the pane stay in the app's own browser storage on the device, separate from the user's other browsers. Cowork sessions keep them until the user clicks **Clear browsing data** in the pane's menu. Code sessions clear them when the app quits, unless the user sets **Keep cookies** in the pane's menu to **Shared** or **Per session**.

### Turn on the built-in browser

The built-in browser is off by default. Set [`builtinBrowserEnabled`](/docs/third-party/claude-desktop/configuration#builtinbrowserenabled) to `true` in your managed configuration, under **General restrictions** in the **Workspace** section of the [in-app configuration window](/docs/third-party/claude-desktop/in-app-configuration). The change takes effect after Claude Desktop restarts.

Also allow `releases.claude.com` through your firewall, because Claude Desktop contacts it for the [site safety check](#site-safety-check). If the app can't complete a check, users can keep browsing the site, but Claude can't read or act on it.

If your devices use a [bootstrap server](/docs/third-party/claude-desktop/bootstrap), set the key in the configuration the server returns, because a value set only on the device leaves the browser off. If you manage the app from the Enterprise Admin Console, use [the console's **Built-in browser** switch](#manage-the-built-in-browser-from-the-enterprise-admin-console) instead.

### Restrict which sites Claude can open

[`builtinBrowserDefaultDomainPolicy`](/docs/third-party/claude-desktop/configuration#builtinbrowserdefaultdomainpolicy) decides whether Claude can open every site except the ones you block, or only the sites you allow.

| Value            | Behavior                                                                                                                                                  |
| ---------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Unset or `allow` | Claude can open every site except the entries in [`builtinBrowserBlockedDomains`](/docs/third-party/claude-desktop/configuration#builtinbrowserblockeddomains) |
| `block`          | Claude can open only the entries in [`builtinBrowserAllowedDomains`](/docs/third-party/claude-desktop/configuration#builtinbrowseralloweddomains)              |

For example, this configuration lets Claude open only a documentation site and a wiki:

```json theme={null}
{
  "builtinBrowserEnabled": true,
  "builtinBrowserDefaultDomainPolicy": "block",
  "builtinBrowserAllowedDomains": ["docs.example.com", "wiki.example.com", "*.wiki.example.com"]
}
```

If you use `block`, also list the hosts that your allowed sites load scripts, images, and data from, because every page in the pane loads content only from sites the policy allows. To keep the default `allow` policy and block specific sites instead, list them in `builtinBrowserBlockedDomains`, for example `["example.com", "*.example.org"]`. A hostname entry also covers its `www.` form but no other subdomain, and a `*.` wildcard covers every subdomain but not the bare domain. The [configuration reference](/docs/third-party/claude-desktop/configuration#builtinbrowseralloweddomains) lists the full entry format.

The site policy restricts Claude, not the user. A user can still type a blocked site's address and open the page. The pane then shows the banner "This site is blocked by your organization's policy" and Claude's tools stay off on that page. The page loads content only from its own site and from sites the policy allows, so under `block` it often renders incompletely.

If [`coworkEgressAllowedHosts`](/docs/third-party/claude-desktop/configuration#coworkegressallowedhosts) lists specific hosts, Claude can open only sites on that list in the built-in browser, even when the browser's own site lists allow more.

The example is plain JSON, which is the form a [bootstrap server](/docs/third-party/claude-desktop/bootstrap) response and the Linux managed file use. For a macOS profile or the Windows registry, encode the same values as the [Value types](/docs/third-party/claude-desktop/configuration#value-types) section describes.

### Manage the built-in browser from the Enterprise Admin Console

If you manage the app from the [Enterprise Admin Console](/docs/third-party/claude-desktop/admin-console), you control the built-in browser from the console instead of with these keys. In **Organization settings** on claude.ai, open the **Capabilities** page and turn on the **Built-in browser** switch under **Data sources**. The change takes effect when users restart Claude Desktop. Also allow `releases.claude.com` through your firewall, because Claude Desktop contacts it for the [site safety check](#site-safety-check).

Once the switch is on, **Browser site permissions** appears below it. Click the **Manage site permissions** button to choose whether Claude can act on every site except the ones you block, or only on the sites you allow, and add those sites in the same dialog. These are the same site permissions [Claude in Chrome](#claude-in-chrome) uses, and changes to them apply without a restart.

## Site safety check

Claude in Chrome and the built-in browser both check public website addresses against Anthropic's site safety list. Anthropic retains basic Claude in Chrome safety check logs, containing the user's account ID, IP address, timestamp of the request, and their OS/Chrome version. No URL, page content, prompt content, or anything else about the request is stored. For the built-in browser, the account ID is empty unless your organization uses the Enterprise Admin Console, because only a console-managed app sends the check as a signed-in user.

## Related

* [`builtinBrowserEnabled` in the configuration reference](/docs/third-party/claude-desktop/configuration#builtinbrowserenabled)
* [Web search and web fetch](/docs/third-party/claude-desktop/web-tools)
* [Telemetry and egress](/docs/third-party/claude-desktop/telemetry)
* [Deploy with Enterprise Admin Console](/docs/third-party/claude-desktop/admin-console)

third-party/claude-desktop/feature-matrix Changed · +4 / -1 lines

from line 29
2929| Projects | ✓ | ✓ |
3030| Code execution for analysis | ✓ | ✓ |
3131| Web search | ✓ | ✓ § |
32| [Built-in browser](/docs/third-party/claude-desktop/browser) | ✓ | ✓ |
3233| File access, upload, and export | ✓ | ✓ |
3334| Local MCP | ✓ | ✓ |
3435| Remote MCP | ✓ | ✓ |
from line 44
4344| Mobile | ✓ | — |
4445| claude.ai web-based access | ✓ | — |
4546| Voice mode | ✓ | — |
46| Claude in Chrome | ✓ | |
47| [Claude in Chrome](/docs/third-party/claude-desktop/browser#claude-in-chrome) | ✓ | ✓ ‖ |
4748| Claude Design | ✓ | — |
4849| Claude Security | ✓ | — |
4950| Claude Tag | ✓ | — |
from line 55
5455† Memory in Claude Desktop on 3P is stored on the device, not on Anthropic infrastructure. Users can review, delete, or pause it under **Settings → Cowork → Memory**; see [Memory](/docs/third-party/claude-desktop/data-storage#memory). Chat-history search and nightly summary generation are not available in Chat on 3P.
5556 
5657¶ Cowork's Automatically approve and Skip all approvals modes are not available for Claude Enterprise organizations.
58 
59‖ Claude in Chrome works with Claude Desktop on 3P only in organizations managed from the [Enterprise Admin Console](/docs/third-party/claude-desktop/admin-console).
5760 
5861## Admin features
5962 

third-party/claude-desktop/admin-console Changed · +2 / -0 lines

from line 101
101101 
102102Most of these settings can also differ per group of users, on the **Permission policies** page under **People**, as described under [Per-group permission policies](#per-group-permission-policies).
103103 
104To turn on the built-in browser, open the **Capabilities** page in **Organization settings**, outside the **Desktop 3P** section, and turn on the **Built-in browser** switch under **Data sources**, as described under [Manage the built-in browser from the Enterprise Admin Console](/docs/third-party/claude-desktop/browser#manage-the-built-in-browser-from-the-enterprise-admin-console).
105 
104106### Choose how users authenticate to your provider
105107 
106108<Tip>

third-party/claude-desktop/telemetry Changed · +2 / -1 lines

from line 263
263263| Hosts in `coworkEgressAllowedHosts` | Sandbox web access is configured |
264264| `api.anthropic.com` | [Code](/docs/third-party/claude-desktop/code) sessions can use Web Fetch and [`skipWebFetchPreflight`](/docs/third-party/claude-desktop/configuration#skipwebfetchpreflight) is not `true` (Claude Code's Web Fetch [domain check](/docs/third-party/claude-desktop/web-tools#web-fetch)) |
265265| `claude.ai`, `api.anthropic.com`, `storage.googleapis.com` | [Import from claude.ai](/docs/third-party/claude-desktop/import) is enabled (`claudeAiImport` with `enabled` set to `true`). Used only while a user signs in to claude.ai and fetches an export in the import wizard; importing a downloaded export file needs none of them |
266| `releases.claude.com` | The [built-in browser](/docs/third-party/claude-desktop/browser) is turned on (`builtinBrowserEnabled` set to `true`), for its [site safety check](/docs/third-party/claude-desktop/browser#site-safety-check) |
266267| `downloads.claude.ai` | [SSH remote sessions](/docs/third-party/claude-desktop/ssh-remote-sessions) are enabled (`sshHostAllowlist` set). With the offline installer, needed only for connections to hosts other than Linux x64 and arm64, because that installer bundles the remote components for those hosts (see [Host requirements](/docs/third-party/claude-desktop/ssh-remote-sessions#host-requirements)) |
267268 
268269## Disabling all Anthropic-bound connections
269270 
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.
271With `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. Turning on the [built-in browser](/docs/third-party/claude-desktop/browser) adds `releases.claude.com`, which the app contacts for the built-in browser's site safety check.
271272 
272273An 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.
273274