Browser Use MCP Server

What is Browser Use MCP Server about?

Browser Use MCP Server is an MCP server that lets AI agents drive web browsers programmatically. It integrates with the browser-use library and uses Playwright for automation, offering real‑time VNC streaming so users can watch the browser actions as they happen.

How to use Browser Use MCP Server?

1. Install prerequisites – install uv, playwright, and mcp-proxy as described in the README.
2. Set environment variables in a .env file (e.g., OPENAI_API_KEY).
3. Install dependencies with uv sync and install Playwright browsers.
4. Run the server:
   • SSE mode: uv run server --port 8000
   • stdio mode: browser-use-mcp-server run server --port 8000 --stdio --proxy-port 9000
5. Configure the client by adding an entry to the client’s mcp.json (see the README for SSE and stdio examples).
6. (Optional) Run via Docker – build the image and start the container exposing ports 8000 (API) and 5900 (VNC).

Key features of Browser Use MCP Server

• Browser automation for AI agents using Playwright.
• Dual transport support – Server‑Sent Events (SSE) and stdio protocols.
• VNC streaming to monitor automation in real time.
• Asynchronous task handling for long‑running browser operations.
• Docker-ready image for consistent deployment.
• Easy configuration for popular AI clients such as Cursor, Windsurf, and Claude.

Use cases of Browser Use MCP Server

• Web research: Agents can navigate to sites, extract content, and summarize results.
• Data collection: Automate scraping of dynamic pages that require JavaScript execution.
• Automated testing: Run UI tests driven by AI prompts.
• Live demo environments: Show agents interacting with web pages while viewers watch via VNC.
• Integration with AI assistants: Enable chat assistants to perform real‑time web actions on behalf of users.

FAQ from the Browser Use MCP Server

Q: Do I need a Chrome binary? A: By default Playwright downloads Chromium. You can optionally specify a custom Chrome path via the CHROME_PATH environment variable.

Q: How do I provide my OpenAI API key? A: Set OPENAI_API_KEY in the .env file or export it in the shell before launching the server.

Q: Can I run the server without Docker? A: Yes, the README includes native install steps using uv and Playwright.

Q: What is the purpose of the PATIENT flag? A: When true, API calls will wait for the browser task to finish before returning a response.

Q: How do I change the VNC password? A: Provide a text file with the desired password and mount it as a secret when running the Docker container, as shown in the README.

browser-use-mcp-server

An MCP server that enables AI agents to control web browsers using browser-use.

🌐 Want to Vibe Browse the Web? Open-source AI-powered web browser - Vibe Browser.

🔗 Managing multiple MCP servers? Simplify your development workflow with agent-browser

Prerequisites

• uv - Fast Python package manager
• Playwright - Browser automation
• mcp-proxy - Required for stdio mode

# Install prerequisites
curl -LsSf https://astral.sh/uv/install.sh | sh
uv tool install mcp-proxy
uv tool update-shell

Environment

Create a .env file:

OPENAI_API_KEY=your-api-key
CHROME_PATH=optional/path/to/chrome
PATIENT=false  # Set to true if API calls should wait for task completion

Installation

# Install dependencies
uv sync
uv pip install playwright
uv run playwright install --with-deps --no-shell chromium

Usage

SSE Mode

# Run directly from source
uv run server --port 8000

stdio Mode

# 1. Build and install globally
uv build
uv tool uninstall browser-use-mcp-server 2>/dev/null || true
uv tool install dist/browser_use_mcp_server-*.whl

# 2. Run with stdio transport
browser-use-mcp-server run server --port 8000 --stdio --proxy-port 9000

Client Configuration

SSE Mode Client Configuration

{
  "mcpServers": {
    "browser-use-mcp-server": {
      "url": "http://localhost:8000/sse"
    }
  }
}

stdio Mode Client Configuration

{
  "mcpServers": {
    "browser-server": {
      "command": "browser-use-mcp-server",
      "args": [
        "run",
        "server",
        "--port",
        "8000",
        "--stdio",
        "--proxy-port",
        "9000"
      ],
      "env": {
        "OPENAI_API_KEY": "your-api-key"
      }
    }
  }
}

Config Locations

Client	Configuration Path
Cursor	./.cursor/mcp.json
Windsurf	~/.codeium/windsurf/mcp_config.json
Claude (Mac)	~/Library/Application Support/Claude/claude_desktop_config.json
Claude (Windows)	%APPDATA%\Claude\claude_desktop_config.json

Features

• Browser Automation: Control browsers through AI agents
• Dual Transport: Support for both SSE and stdio protocols
• VNC Streaming: Watch browser automation in real-time
• Async Tasks: Execute browser operations asynchronously

Local Development

To develop and test the package locally:

1. Build a distributable wheel:

   # From the project root directory
   uv build
   

2. Install it as a global tool:

   uv tool uninstall browser-use-mcp-server 2>/dev/null || true
   uv tool install dist/browser_use_mcp_server-*.whl
   

3. Run from any directory:

   # Set your OpenAI API key for the current session
   export OPENAI_API_KEY=your-api-key-here
   
   # Or provide it inline for a one-time run
   OPENAI_API_KEY=your-api-key-here browser-use-mcp-server run server --port 8000 --stdio --proxy-port 9000
   

4. After making changes, rebuild and reinstall:

   uv build
   uv tool uninstall browser-use-mcp-server
   uv tool install dist/browser_use_mcp_server-*.whl
   

Docker

Using Docker provides a consistent and isolated environment for running the server.

# Build the Docker image
docker build -t browser-use-mcp-server .

# Run the container with the default VNC password ("browser-use")
# --rm ensures the container is automatically removed when it stops
# -p 8000:8000 maps the server port
# -p 5900:5900 maps the VNC port
docker run --rm -p8000:8000 -p5900:5900 browser-use-mcp-server

# Run with a custom VNC password read from a file
# Create a file (e.g., vnc_password.txt) containing only your desired password
echo "your-secure-password" > vnc_password.txt
# Mount the password file as a secret inside the container
docker run --rm -p8000:8000 -p5900:5900 \
  -v $(pwd)/vnc_password.txt:/run/secrets/vnc_password:ro \
  browser-use-mcp-server

Note: The :ro flag in the volume mount (-v) makes the password file read-only inside the container for added security.

VNC Viewer

# Browser-based viewer
git clone https://github.com/novnc/noVNC
cd noVNC
./utils/novnc_proxy --vnc localhost:5900

Default password: browser-use (unless overridden using the custom password method)

Example

Try asking your AI:

open https://news.ycombinator.com and return the top ranked article

Support

For issues or inquiries: cobrowser.xyz

Star History