MCP server Browser Use

WHAT IT CONNECTS

What MCP server Browser Use gives an AI Agent

• **Browser Control**
• Automated browser interactions via natural language
• Navigation, form filling, clicking, and scrolling capabilities
• Tab management and screenshot functionality
• Cookie and state management
• **Agent System**
• Custom agent implementation in custom_agent.py
• Vision-based element detection
• Structured JSON responses for actions
• Message history management and summarization
• **Configuration**
• Environment-based configuration for API keys and settings
• Chrome browser settings (debugging port, persistence)
• Model provider selection and parameters
• Integration with browser-use library for advanced browser control
• Custom browser automation capabilities
• Agent-based interaction system with vision capabilities
• Persistent state management
• Customizable model settings
• Operating Systems (Linux, macOS, Windows; we haven't tested for Docker or Microsoft WSL)
• Python 3.11 or higher
• uv (fast Python package installer)
• Chrome/Chromium browser
• [Claude Desktop](https://claude.ai/download)
• Clone the repository:
• Create and activate virtual environment:
• Install dependencies:
• Start the server
• Navigation: Go to URLs, back/forward, refresh
• Interaction: Click, type, scroll, hover
• Forms: Fill forms, submit, select options
• State: Get page content, take screenshots
• Tabs: Create, close, switch between tabs
• Vision: Find elements by visual appearance
• Cookies & Storage: Manage browser state
• Fork this repository.
• Create your feature branch: `git checkout -b my-new-feature`.
• Commit your changes: `git commit -m 'Add some feature'`.
• Push to the branch: `git push origin my-new-feature`.
• Submit a pull request.