Anchor Browser MCP server

Connect Anchor Browser to Claude, ChatGPT, Cursor, Claude Code, Codex, Gemini, GitHub Copilot and any other MCP client, for your whole team. Metorial adds security, governance, and tracing, and gives everyone one Magic MCP URL to connect.

What you can do with the Anchor Browser MCP server

Ask your agent in plain language. Each of these maps to a real tool on the server.

  • Use the manage extensions tool in Anchor Browser
  • Use the fetch webpage content tool in Anchor Browser
  • Use the end session tool in Anchor Browser
  • Use the manage agent tool in Anchor Browser
  • Use the create browser session tool in Anchor Browser
  • Use the browser control tool in Anchor Browser

Supported Tools

manage_extension

Manage Extensions

List, retrieve, or delete Chrome extensions configured on your account. Extensions can be loaded into browser sessions for ad blocking, privacy tools, or custom functionality.

fetch_webpage

Fetch Webpage Content

Fetch the content of a webpage as HTML or Markdown. Can be used standalone (without a session) or within an existing session for pages that require authentication or specific browser state.

end_session

End Session

Terminate one or all active browser sessions. Provide a specific session ID to end a single session, or set endAll to true to terminate all active sessions at once.

manage_agent

Manage Agent

List uploaded agent resources, pause, or resume a running AI agent within an active browser session.

create_session

Create Browser Session

Start a new cloud-hosted Chromium browser session with configurable proxy, CAPTCHA solving, ad blocking, stealth mode, and more. Returns a session ID, CDP WebSocket URL for programmatic control, and a live view URL for real-time observation.

browser_control

Browser Control

Perform OS-level browser interactions within an active session. Supports mouse clicks, double clicks, drag-and-drop, scrolling, typing text, keyboard shortcuts, navigation, and clipboard operations. Useful for interacting with elements not accessible via standard browser APIs.

get_active_sessions

Get Active Sessions

Retrieve the status of all currently active browser sessions. Returns a lightweight summary with count and individual session statuses, tags, and creation timestamps.

manage_recording

Manage Recording

List, pause, or resume session recordings. Recordings capture browser session activity for later review and debugging.

get_session

Get Session Details

Retrieve detailed information about a specific browser session including its status, duration, configuration, credits used, and associated tags.

signal_event

Signal Event

Send a named event with a custom data payload to an active browser session. Useful for injecting external data (e.g. MFA codes, dynamic values) into a running browser automation workflow.

manage_identity

Manage Identities

Create, list, retrieve, update, or delete identities. Identities store user credentials (username/password, authenticator secrets, custom fields) for automated login flows on target applications.

manage_profile

Manage Browser Profile

Create, retrieve, list, or delete browser profiles. Profiles persist cookies, local storage, and cache from a session for reuse across future sessions, maintaining authenticated states without re-logging in.

screenshot_webpage

Screenshot Webpage

Capture a webpage as a downloadable PNG screenshot, standalone or within an existing session. Supports configurable viewport size, quality, full-page capture, and an optional S3 upload target.

perform_web_task

Perform AI Web Task

Submit a natural language prompt and an AI agent will autonomously navigate and complete a task in a browser. Supports multiple AI agents including browser-use, OpenAI CUA, Gemini, and Anthropic CUA. Can run synchronously (returns result directly) or asynchronously (returns a workflow ID to poll for status).

manage_integration

Manage Integrations

List, create, or delete third-party integrations configured on your Anchor Browser account (e.g. 1Password service accounts).

manage_application

Manage Applications

Create, list, retrieve, update, or delete application definitions. Applications represent target websites/services that can have authentication flows and identities configured for automated login.

list_sessions

List Sessions

Retrieve a paginated list of browser sessions with optional filtering by status, tags, domains, and date range. Returns session metadata including status, duration, credits used, and proxy information.

manage_batch

Manage Batch Sessions

Create, list, get status, cancel, delete, or retry batch browser sessions. Batch sessions allow creating multiple browser sessions in a single operation (up to 1000), with progress tracking and retry capabilities.

check_web_task_status

Check AI Task Status

Check the status and result of an asynchronous AI web task. Use the workflow ID returned from a previous async Perform AI Web Task call.

get_page_pdf

Get Page PDF

Generate a downloadable PDF from a webpage, optionally using an existing browser session for authenticated pages.

get_session_pages

Get Session Pages

List the open pages in a browser session, including each page ID, title, URL, and live view URL.

Connect Anchor Browser to your AI client

Every client uses the same Magic MCP URL, and so does any other MCP client. Add it once and sign in with SSO.

  1. Enable Anchor Browser in Metorial. In your Metorial portal, enable the Anchor Browser MCP server and sign in with the account that owns the data. Access stays governed by your team policies.
  2. Add a custom connector. Open Customize, then Connectors. Select Add, then Custom, then Web.
  3. Paste your Metorial MCP URL. Name it Metorial, paste your Magic MCP URL (<your-magic-mcp-url>) and continue.
  4. Sign in. Select Add and sign in to load Anchor Browser tools.

Run Anchor Browser through the Metorial gateway

One governed layer for every app your agents reach, not a separate connector per tool.

  • Give Anchor Browser and every other app to your whole team through one MCP gateway, behind your SSO.
  • Scope which teams and agents can use Anchor Browser tools with role-based access control, and trace every call.
  • Prefer to run it yourself? Metorial is open source and self-hostable.

More integrations teams use with Anchor Browser

Notion

Create, read, update, and archive pages and databases in a Notion workspace. Manage blocks (paragraphs, lists, headings, embeds, etc.) within pages. Query databases with filters and sorts across rich property types including text, numbers, dates, selects, relations, and formulas. Search across pages and databases by title. Add and read comments on pages and blocks. Upload files to pages. Manage workspace users and retrieve user profiles.

Google Sheets

Create, read, and update spreadsheets and their cell data. Read and write values to individual cells, ranges, or multiple ranges using A1 notation or named ranges. Apply cell formatting including text styles, backgrounds, borders, number formats, and conditional formatting. Manage sheets (tabs) within a spreadsheet—add, delete, copy, rename, and reorder them. Create and manage embedded charts, pivot tables, filter views, data validation rules, protected ranges, named ranges, and merged cells. Perform batch operations to apply multiple updates atomically.

GitHub

Manage repositories, issues, and pull requests. Create and configure branches, star repositories, review code, and merge changes. Automate CI/CD workflows with GitHub Actions, manage workflow runs, secrets, and artifacts. Track issues with labels, milestones, and assignees. Search across code, repositories, issues, and users. Manage organizations, teams, and memberships. Create and manage projects, gists, packages, deployments, and environments. Access security alerts including code scanning, secret scanning, and Dependabot alerts. Read and write file contents in repositories. Manage webhooks, notifications, and codespaces.

Salesforce

Manage CRM data including Accounts, Contacts, Leads, Opportunities, Cases, and custom objects. Create, read, update, and delete records. Query data using SOQL and search across objects using SOSL. Perform bulk data operations for large-scale imports, exports, and migrations. Execute composite requests to batch multiple operations in a single API call. Access analytics, reports, and dashboards. Manage files and attachments associated with records. Interact with Chatter feeds, posts, and groups for social collaboration. Manage org metadata including custom objects, fields, layouts, and workflows. Query data using GraphQL for precise data retrieval across related objects.

Sharepoint

Manage SharePoint sites, document libraries, lists, and files. Create, read, update, and delete lists and list items with custom columns. Resolve site users to numeric Person/Group LookupId values. Upload, download, move, copy, and version files in document libraries. Search across sites, files, folders, lists, and list items using Microsoft Search. Manage permissions at site, list, and item levels with granular access control. Define and manage content types and site columns. Retrieve site properties and search for sites across Microsoft 365.

Microsoft Outlook

Send, read, reply to, forward, and manage email messages in user mailboxes. Organize messages into folders, apply categories, flags, and importance levels. Manage file and item attachments. Create, update, delete, and respond to calendar events and meetings. Find available meeting times, manage attendees, handle recurrence, and work with shared or delegated calendars. Create, read, update, and delete contacts, organize them into contact folders, and manage contact photos. Manage tasks and task lists via Microsoft To Do, including due dates, reminders, recurrence, and checklist items. Support for Focused Inbox, @-mentions, mail tips, send-on-behalf, and send-as capabilities.

Technical notes for Anchor Browser

Automate web-based workflows using cloud-hosted browser sessions. Create, configure, and manage Chromium browser instances with proxy support, CAPTCHA solving, stealth mode, and ad blocking. Execute AI-powered web tasks by submitting natural language prompts to autonomous agents (browser-use, OpenAI, Gemini, Anthropic). Manage browser profiles to persist cookies and authenticated states across sessions. Perform OS-level controls including mouse clicks, keyboard input, scrolling, drag-and-drop, and clipboard operations. Fetch web content as text, screenshots, or PDFs without persistent sessions. Upload and manage Chrome extensions. Create and manage batch browser sessions. Define applications with authentication flows and manage identity credentials for automated logins. Record, pause, and resume browser sessions for review. Coordinate real-time events between external systems and active sessions (e.g., injecting MFA codes). Upload resources for AI agent access and manage third-party integrations.

Frequently asked questions

Common questions about connecting Anchor Browser to AI agents with Metorial.

  1. How many tools does the Anchor Browser MCP server have?
    The Anchor Browser MCP server exposes 21 tools, including Manage Extensions, Fetch Webpage Content, End Session. Each one is governed and traced through Metorial.
  2. Anchor Browser exposes tools your agents call on demand; it does not publish event triggers yet. Everything still runs through one governed MCP URL.
  3. Any MCP client, including VS Code, Windsurf, Zed, OpenCode and Grok. Each one reaches the Anchor Browser MCP server through the same Metorial URL.
  4. Use role-based access control to decide which teams, users, and agents can use Anchor Browser and which of its tools they can call.
  5. Yes. Metorial is open source, so you can run the Anchor Browser MCP server yourself or use the hosted gateway.

Connect Anchor Browser to production AI agents

See how Metorial gives your team governed access to Anchor Browser, with tracing and security controls built in.