MCP

Give your agent a browser in one config block.

Paste the config for your client and Claude Code, Cursor, Claude Desktop or Windsurf can run browser tasks on stealth cloud browsers and read the result back.

Get an API key MCP docs

ChatGPT in developer mode with the Browser Use MCP server added: a browser task in, the result back.

6
tools on the hosted server: $0.02 / hour
browser time inside a run, plus model tokens: $15
of credit for eligible new Google, GitHub or Microsoft signups

Cloud, or your own Chrome.

The hosted server hands a whole task to an agent on a cloud browser and returns the result. The local stdio server, browser-harness-mcp, exposes click, type, read and screenshot on the Chrome you are logged into. For agents that would rather write their own browser code, see the CLI and skill.

claude mcp add -t http \  -H "x-browser-use-api-key: YOUR_API_KEY" \  browser-use https://api.browser-use.com/v3/mcp

terminal·Streamable HTTP · API key header

The six tools

run_session: Create a session and run a task. Options: keep_alive, model, output_schema, profile_id.
get_session: Status, step count, cost so far, and the live URL.
send_task: A follow-up task to an idle keep-alive session.
stop_session: Stop the task, or destroy the whole session.
get_session_messages: The agent's actions, reasoning and results.
list_sessions: Recent sessions with status and cost.

Questions people ask

Which clients work?

Any MCP client that speaks streamable HTTP with headers. Claude Code, Claude Desktop, Cursor and Windsurf are documented. The local stdio server works with Claude Code, Devin, Cursor and other stdio clients.

Where do I get the key?

Create one at cloud.browser-use.com under Settings, API keys. Eligible new Google, GitHub or Microsoft signups get $15 of credit once, no card.

What does a task cost?

Model tokens plus browser time at $0.02 per browser-hour. On our hardest internal set the agent solved 82% of 106 tasks at 17¢ per solved task.

Hosted or local?

Hosted when you want to hand off a whole task and get the result back on a stealth cloud browser. Local when your coding agent should drive your own logged-in Chrome step by step.

Can it return JSON?

Yes. Pass output_schema to run_session and the result matches your schema.