📌Overview

Purpose: To provide a powerful browser automation system enabling AI agents to interact with web browsers using natural language.

Overview: This repository hosts the server for the browser-use library, leveraging Anthropic's Model Context Protocol (MCP) to facilitate seamless browser automation. It allows AI-driven interactions in web environments, enhancing the capabilities of AI agents.

Key Features:

• Browser Control: Offers automated interactions such as navigation, form filling, and screenshot capturing through natural language commands, along with tab and cookie management.

• Agent System: Includes a customizable agent implementation with vision-based element detection and structured JSON responses for actions, enabling robust agent interactions and message history management.

• Configuration: Features environment-based settings for API keys and Chrome configuration, allowing flexible model provider selection and easy adaptation to different workflows.

MCP server w/ Browser Use

MCP server for browser-use.

Overview

This repository contains the server for the browser-use library, which provides a powerful browser automation system that enables AI agents to interact with web browsers through natural language. The server is built on Anthropic's Model Context Protocol (MCP) and provides seamless integration with the browser-use library.

Features

1. Browser Control

• Automated browser interactions via natural language
• Navigation, form filling, clicking, and scrolling capabilities
• Tab management and screenshot functionality
• Cookie and state management

2. Agent System

• Custom agent implementation in custom_agent.py
• Vision-based element detection
• Structured JSON responses for actions
• Message history management and summarization

3. Configuration

• Environment-based configuration for API keys and settings
• Chrome browser settings (debugging port, persistence)
• Model provider selection and parameters

Dependencies

This project relies on the following Python packages:

Components

Resources

The server implements a browser automation system with:

• 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

Requirements

• Operating Systems: Linux, macOS, Windows (not tested for Docker or Microsoft WSL)
• Python 3.11 or higher
• uv (fast Python package installer)
• Chrome/Chromium browser
• Claude Desktop

Quick Start

Claude Desktop Config Paths

• MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%/Claude/claude_desktop_config.json

Installing via Smithery

To install Browser Use for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @JovaniPink/mcp-browser-use --client claude

"mcpServers": {
  "mcp_server_browser_use": {
    "command": "uvx",
    "args": [
      "mcp-server-browser-use",
    ],
    "env": {
      "OPENAI_ENDPOINT": "https://api.openai.com/v1",
      "OPENAI_API_KEY": "",
      "ANTHROPIC_API_KEY": "",
      "GOOGLE_API_KEY": "",
      "AZURE_OPENAI_ENDPOINT": "",
      "AZURE_OPENAI_API_KEY": "",
      "ANONYMIZED_TELEMETRY": "false",
      "CHROME_PATH": "",
      "CHROME_USER_DATA": "",
      "CHROME_DEBUGGING_PORT": "9222",
      "CHROME_DEBUGGING_HOST": "localhost",
      "CHROME_PERSISTENT_SESSION": "false",
      "MCP_MODEL_PROVIDER": "anthropic",
      "MCP_MODEL_NAME": "claude-3-5-sonnet-20241022",
      "MCP_TEMPERATURE": "0.3",
      "MCP_MAX_STEPS": "30",
      "MCP_USE_VISION": "true",
      "MCP_MAX_ACTIONS_PER_STEP": "5",
      "MCP_TOOL_CALL_IN_CONTENT": "true"
    }
  }
}

Environment Variables

Key environment variables:

# API Keys
ANTHROPIC_API_KEY=anthropic_key

# Chrome Configuration
# Optional: Path to Chrome executable
CHROME_PATH=/path/to/chrome
# Optional: Chrome user data directory
CHROME_USER_DATA=/path/to/user/data
# Default: 9222
CHROME_DEBUGGING_PORT=9222
# Default: localhost
CHROME_DEBUGGING_HOST=localhost
# Keep browser open between tasks
CHROME_PERSISTENT_SESSION=false

# Model Settings
# Options: anthropic, openai, azure, deepseek
MCP_MODEL_PROVIDER=anthropic
# Model name
MCP_MODEL_NAME=claude-3-5-sonnet-20241022
MCP_TEMPERATURE=0.3
MCP_MAX_STEPS=30
MCP_USE_VISION=true
MCP_MAX_ACTIONS_PER_STEP=5

Development

Setup

1. Clone the repository:

git clone https://github.com/JovaniPink/mcp-browser-use.git
cd mcp-browser-use

2. Create and activate virtual environment:

python -m venv .venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

3. Install dependencies:

uv sync

4. Start the server

uv run mcp-browser-use

Debugging

For debugging, use the MCP Inspector:

npx @modelcontextprotocol/inspector uv --directory /path/to/project run mcp-server-browser-use

The Inspector will display a URL for the debugging interface.

Browser Actions

The server supports various browser actions through natural language:

• 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

Security

Some Chrome settings allow the browser to be controlled by the server, which is a security risk. Use with caution. The server is not intended for production environments.

Security details are available in SECURITY.MD.

Contributing

Contributions are welcome. Please follow these steps:

1. Fork this repository.
2. Create your feature branch: git checkout -b my-new-feature.
3. Commit your changes: git commit -m 'Add some feature'.
4. Push to the branch: git push origin my-new-feature.
5. Submit a pull request.

For major changes, open an issue first to discuss your plans. Update tests as appropriate for any changes.