run_browser_agentLABSCO SUMMARY
A single task-level tool, not twenty page-level ones.
The trade is deliberate: instead of the model choosing click, type and scroll one at a time, it hands over one instruction and the browser-use agent works out the steps. That keeps the tool surface tiny and the token cost low, and it means you get less control over how the task is carried out.
What it is
An MCP wrapper around the browser-use automation engine. It exposes a single tool that opens a browser session, runs the agent against your instruction, and returns the final result - the browser lifecycle and cleanup are handled inside.
What you get
- One tool, run_browser_agent, that takes a natural-language task and reports back what happened
- Navigation, form filling, tab control, screenshots and page reading, driven by the browser-use agent
- Browser configuration from environment variables - persistent profiles, proxies and custom Chromium flags - without touching agent code
- A choice of model provider and model, with step and action limits capped per run
- Redaction of proxy settings and debug endpoints from logs, since those can carry credentials
Requirements
Python 3.11+, Google Chrome or Chromium for local automation, and uv for dependency management. Clone, run uv sync, then launch with uv run. Configuration is environment variables: the model provider and name, the provider's own API key, and the browser runtime flags. The project's own security note is the one to read first - driving a full browser grants broad access to the host machine.
Setup effort
Build from source — git clone https://github.com/JovaniPink/mcp-browser-use.git
USE CASES
01
Getting something out of a site with no API
Describe the task once - go here, find this, read that back - and let the agent work out the navigation.
02
Filling in a multi-step web form
State what goes in each field and let the browser session carry the state through the steps.
03
Reusing a signed-in browser profile
Point the environment at a persistent profile so the run starts already logged in, rather than automating the login.
1 tool
Listed in project docs. Your client may show a different list.
BEFORE YOU INSTALL
What to know first
Tools you get
1 tool named in the project's documentation.
Requires
- uv on PATH
- Python 3.11+
- Google Chrome or Chromium
- ANTHROPIC_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/JovaniPink/mcp-browser-use.git
cd mcp-browser-use
uv sync
cp sample.env.env .envIn .env, set the API key for the model provider you use (ANTHROPIC_API_KEY for the default anthropic provider)
MCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"mcp_server_browser_use": {
"command": "uv",
"args": [
"--directory",
"<YOUR_PATH_TO_MCP_BROWSER_USE>",
"run",
"mcp-browser-use"
],
"env": {
"MCP_MODEL_PROVIDER": "anthropic",
"MCP_MODEL_NAME": "claude-3-5-sonnet-20241022"
}
}
}
}<YOUR_PATH_TO_MCP_BROWSER_USE> is the full path of the folder the clone created.
The configuration on this page does not set ANTHROPIC_API_KEY; the project's instructions put it in a .env file. To supply ANTHROPIC_API_KEY without depending on where the server looks for that file, use the block's "env" section.
