run taskLABSCO 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 taskstarts 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 taskreturns the full run including its steps;get task statusreturns just the current statestop task,pause taskandresume taskcontrol a run in flightlist tasksshows every task with its ID and statuscheck balancereports your Browser Use account balance
Requirements
Python 3.10 or later with pip, and a Browser Use API key from cloud.browser-use.com, given on the launch command or in BROWSER_USE_API_KEY. 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
USE CASES
01
Getting data off a site with no API
The instructions describe what to collect and the schema describes the shape it should arrive in.
02
Stepping in on a run that is going wrong
A task can be paused mid-flight, looked at, and then resumed or stopped — rather than watched to completion or killed blind.
03
Checking on a long automation
Status alone for a quick check, or the full run with its steps when you need to see where it went.
04
Keeping track of what is running
Every task with its ID and status in one call, which is the view you need before starting another.
05
Seeing what you have spent
Account balance from inside the session, so cloud browsing cost is visible before the next task is queued.
8 tools
Listed in project docs. Your client may show a different list.
get taskget task statusstop taskpause taskresume tasklist taskscheck balanceBEFORE YOU INSTALL
What to know first
Tools you get
8 tools named in the project's documentation.
Requires
Python 3.10 or later, with pip
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
pip install simple-browser-use-mcpMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"browser-use": {
"command": "simple-browser-use-mcp",
"args": [
"--api-key",
"<YOUR_BROWSER_USE_API_KEY>"
]
}
}
}pip install simple-browser-use-mcp puts the simple-browser-use-mcp command on your PATH; if your client cannot find it, use the command's full path. <YOUR_BROWSER_USE_API_KEY> is your key from cloud.browser-use.com, or drop the two --api-key arguments and set BROWSER_USE_API_KEY in the entry's env.
