browser-use-mcp-server

Overview

The browser-use-mcp-server provides a robust implementation of the Model Context Protocol for browser automation. It allows AI agents to interact with web pages, perform actions like clicking, scrolling, and form filling, and extract information. The server supports both SSE and stdio transport modes and includes VNC streaming for real-time visualization of browser automation.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• open

  Open a URL in the browser

  Try:open https://news.ycombinator.comTry:navigate to google.com

Note: Only one tool was referenced in the README, mentioned in the example section. No explicit tool documentation was provided in the README.

Comparable tools

Installation

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

OPENAI_API_KEY=your-api-key
CHROME_PATH=optional/path/to/chrome
PATIENT=false

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

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

FAQ

How can I view the browser automation in real-time?

The server supports VNC streaming. Use a VNC client to connect to localhost:5900 with the default password 'browser-use', or use a browser-based viewer with noVNC.

Which AI models are supported?

The server uses browser-use which supports multiple AI providers. You'll need to set your API key (like OpenAI) in the environment configuration.

Compare browser-use-mcp-server with