Labsco
MCP SERVER

Browser Use

by mhazarabad

Hand a browser task to Browser Use's cloud as written instructions, then watch it, pause it, resume it or stop it — and check what it is costing you.

Browser Automation, Control & Screenshots
Summary
Browser automation you describe, then supervise.

The task goes out as instructions and comes back as structured data, with pause, resume and stop available the whole time it runs.

What it is

A Python server over the Browser Use cloud API. It starts a browser automation task from written instructions, optionally against a JSON schema for structured output, and exposes the controls for managing the run.

What you get
  • `run task` starts an automation from written instructions and waits for it to finish
  • structured_output takes a JSON schema, so the result comes back shaped instead of as prose
  • `get task` returns the full run including its steps; `get task status` returns just the current state
  • `stop task`, `pause task` and `resume task` control a run in flight
  • `list tasks` shows every task with its ID and status
  • `check balance` reports your Browser Use account balance
Requirements

Python, with uv or pip, and a Browser Use API key from cloud.browser-use.com given on the launch command. The browsing itself runs in Browser Use's cloud, not on your machine.

Setup effort

One command plus a key — pip install simple-browser-use-mcp, then supply credentials