Browser Use MCP server

• get_sessionFree

  Get current status and output of a session. Call this repeatedly to poll for task completion. Returns status (created, idle, running, stopped, timed_out, error), step count, output, cost breakdown, and live URL.

• get_session_messagesFree

  Get the agent messages/steps for a session. Shows what the agent is doing including browser actions, reasoning, and results. Use after= parameter for pagination to get new messages since your last check.

• list_browser_profilesFree

  List all available cloud browser profiles for the authenticated project. Profiles store persistent authentication (cookies, sessions) for websites requiring login. Use this BEFORE attempting any authenticated tasks. Show profiles to the user and let them choose, then pass the selected profile_id to run_session.

• list_sessionsFree

  List recent sessions for the authenticated project, with status and cost info.

• run_sessionwrite actionFree

  Create a new browser agent session and run a task. This uses the v3 sandbox-based agent that supports long-running sessions, workspaces, and keep-alive. After creating a session, call get_session to poll for status and output. For tasks requiring authentication, use list_browser_profiles first to get a profile_id.

• send_taskwrite actionFree

  Send a follow-up task to an existing keep-alive session. The session must be in idle status. Use this for multi-turn interactions where you want to reuse the same browser context.

• stop_sessionFree

  Stop a running session. Use strategy "task" to stop only the current task (session stays idle for follow-ups), or "session" (default) to destroy the sandbox entirely.

• Code scan169 source files scanned25/25
• Live reliabilityremote reachable in 322ms20/20
• Tool poisoning7 tool descriptions checked15/15
• Auth qualityAPI key sent as a header8/15
• Maintenancelast push 0 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year; website matches verified namespace10/10

Safety score

93/100

higher than 90% of 875 Scraping and browsing servers

Tools

7

the typical Scraping and browsing server has 7

Tools that change things

29%

typical: 0%. Fewer write tools means less an agent can break

Uptime

100%

of our recent checks; the typical remote Scraping and browsing server answers 100%

Response time

420 ms

faster than 28% of 394 Scraping and browsing servers

GitHub stars

120,244

more than 100% of 595 Scraping and browsing servers

Downloads a week

1,551,803

more than 96% of 355 Scraping and browsing servers with a package

Browser Use: common questions

Is Browser Use MCP server safe?

Yes, by our scan: it is graded A (93/100). Read the Browser Use safety report

How do I install Browser Use?

It runs remotely at api.browser-use.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.

Does Browser Use need an API key?

Yes. The registry entry asks for X-Browser-Use-API-Key.

Is Browser Use maintained?

The last commit was 8 days ago (2026-11-07). The latest release is v0.13.11.

Is Browser Use up?

100% of our last 28 checks got an answer. We check remote servers about four times a day.

What can I use instead of Browser Use?

Servers from other publishers that do the same job: Skyvern MCP server, Fortress MCP server and Kernel MCP Server. Compare all Browser Use alternatives.

How does Browser Use compare with other Scraping and browsing MCP servers?

safety score 93/100 (higher than 90% of 875 Scraping and browsing servers); tools 7 (the typical Scraping and browsing server has 7); tools that change things 29% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.