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 a seamless integration with the browser-use library.

Features

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

Dependencies

This project relies on the following Python packages:

Package	Version	Description

            | [pydantic](https://docs.pydantic.dev/)       | >=2.10.5  | Data validation and settings management using Python type annotations. Provides runtime enforcement of types and automatic model creation. Essential for defining structured data models in the agent.        |

| fastapi | >=0.115.6 | Modern, fast (high-performance) web framework for building APIs with Python 3.7+ based on standard Python type hints. Used to create the server that exposes the agent's functionality. | | uvicorn | >=0.22.0 | ASGI web server implementation for Python. Used to serve the FastAPI application. | | fastmcp | >=0.4.1 | A framework that wraps FastAPI for building MCP (Model Context Protocol) servers. | | python-dotenv | >=1.0.1 | Reads key-value pairs from a .env file and sets them as environment variables. Simplifies local development and configuration management. | | langchain | >=0.3.14 | Framework for developing applications with large language models (LLMs). Provides tools for chaining together different language model components and interacting with various APIs and data sources. | | langchain-openai | >=0.2.14 | LangChain integrations with OpenAI's models. Enables using OpenAI models (like GPT-4) within the LangChain framework. Used in this project for interacting with OpenAI's language and vision models. | | langchain-ollama | >=0.2.2 | Langchain integration for Ollama, enabling local execution of LLMs. |

            | [openai](https://platform.openai.com/docs/api-reference)    | >=1.59.5  | Official Python client library for the OpenAI API. Used to interact directly with OpenAI's models (if needed, in addition to LangChain).                                                                    |

| browser-use | ==0.1.19 | A powerful browser automation system that enables AI agents to interact with web browsers through natural language. The core library that powers this project's browser automation capabilities. | | instructor | >=1.7.2 | Library for structured output prompting and validation with OpenAI models. Enables extracting structured data from model responses. | | pyperclip | >=1.9.0 | Cross-platform Python module for copy and paste clipboard functions. |

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; we haven't 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

On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json On 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

Development Configuration

"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": "",
      // "DEEPSEEK_ENDPOINT": "https://api.deepseek.com",
      // "DEEPSEEK_API_KEY": "",
      // Set to false to disable anonymized telemetry
      "ANONYMIZED_TELEMETRY": "false",
      // Chrome settings
      "CHROME_PATH": "",
      "CHROME_USER_DATA": "",
      "CHROME_DEBUGGING_PORT": "9222",
      "CHROME_DEBUGGING_HOST": "localhost",
      // Set to true to keep browser open between AI tasks
      "CHROME_PERSISTENT_SESSION": "false",
      // Model settings
      "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

Clone the repository:


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

Create and activate virtual environment:

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

Install dependencies:

uv sync

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

I want to note that their are some Chrome settings that are set to allow for the browser to be controlled by the server. This is a security risk and should be used with caution. The server is not intended to be used in a production environment.

Security Details: SECURITY.MD

Contributing

We welcome contributions to this project. Please follow these steps:

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.

For major changes, open an issue first to discuss what you would like to change. Please update tests as appropriate to reflect any changes made.

mcp-browser-use

Categories

Language:

Stars:

Forks: