Anchor Browser MCP: cloud browsers for your AI agent

Bring Anchor Browser into Claude, ChatGPT or Cursor

1. 1Click Connect Anchor Browser free and sign in with your Anchor Browser account.
2. 2Profiles keep cookies and sign-in state, and ending all sessions stops every running browser at once. Switch off profile changes and the end-all tool if your AI app should only browse.
3. 3Add ContextGate to your AI app as a connector or MCP server. The steps for each app are on the Works with page.
4. 4Ask your AI app to open a page in an Anchor Browser session and return it as markdown, then open Activity to see the session and content calls.

Browser tasks for your AI agent

• Start an isolated browser session, with recording if you want it.
• Fetch a page's rendered content as HTML or markdown, or take a PNG screenshot.
• Save a session's cookies and cache as a profile to reuse later.
• Upload files for an agent to use in a session, and list session recordings.
• Coordinate sessions by signaling and waiting for events.

Sessions and sign-ins under watch

• Switch off profile creation, updates and deletes; they're hidden and refused if called.
• Use a policy to block secrets such as passwords from being sent in a call.
• Activity records every session your AI apps start and every page they read.

What you get with Anchor Browser and ContextGate

• Your AI apps can use Anchor BrowserClaude, Cursor, ChatGPT and other AI apps reach Anchor Browser through the one ContextGate connection you add to them.
• You choose which tools they can useSwitch off any Anchor Browser tool you don't want used. It's hidden from your AI apps and refused if called.
• Every call is checked and recordedYour policies check each call (for example, personal data is hidden and secrets are blocked), and Activity keeps a record of it.

ContextGate sees only the tool calls that go through it, not your AI app's built-in tools or your chats.

Anchor Browser tools

Examples of what your AI apps can do in Anchor Browser. You'll see the exact list of tools after you connect it.

• Create ProfileTool to create a new browser profile from an active session. use after ending a session to persist cookies and cache.
• Delete ProfileTool to delete a browser profile by id. use after confirming the profile exists.
• End All SessionsTool to end all active browser sessions. use after confirming a security concern when you need to immediately close every session for the authenticated user.
• End Browser SessionTool to end a specific browser session by id. use after confirming the session id you want to terminate.
• Get ProfileTool to fetch details for a specific browser profile by id. use after you know the profile id and need its settings and session information.
• Get Webpage ContentTool to retrieve rendered content of a webpage in html or markdown format. use when you need to fetch a page’s full content, optionally within an existing browser session.
• List Agent ResourcesTool to list agent resources (files) for a given session. use after establishing a browser session to retrieve agent-uploaded files.
• List All Sessions StatusTool to list the status of all active browser sessions. use after authenticating when you need to retrieve an up-to-date overview of all sessions.
• List ExtensionsTool to list all browser extensions for the authenticated user. use when you need to retrieve available extensions after authentication.
• List ProfilesTool to fetch all stored browser profiles. use when you need an overview of all profiles available to the authenticated user (e.g., after creating or deleting profiles).
• List Session RecordingsTool to list all recordings for a specific browser session. use after confirming the session id.
• List SessionsTool to list all browser sessions. use when you need to retrieve both active and inactive sessions.
• Screenshot WebpageTool to take a screenshot of a specified webpage within a session. use when you need a visual png snapshot of a live page. example: "capture a 1280×720 screenshot of https://example.com".
• Signal EventTool to signal a specific event to be received by other processes or sessions. use when you need real-time coordination across browser sessions after verifying session is active.
• Start Browser SessionTool to start a new browser session with optional customizations. use when you need to programmatically allocate an isolated browser instance with recording, proxy, live view, and feature toggles.
• Update ProfileTool to update an existing browser profile by id. use when you need to modify the profile's description or source session.
• Upload FileTool to upload a file to a browser session as an agent resource. use after starting or referencing a session when you need to provide file inputs (single files or zip archives) for web forms or ai-dri
• Wait for EventTool to wait for a specific event. use when coordinating browser sessions or workflows that depend on an event signal; blocks until the event is signaled or timeout is reached.