-
security-
license-
qualityEnables AI agents to control web browsers via a standardized interface for operations like launching, interacting with, and closing browsers.
The MCP Browser Use Server enables AI agents to interact with web browsers through natural language commands, providing:
Browser Automation: Navigate, click, scroll, and manage tabs via natural language
Form Handling: Fill out and submit forms automatically
Vision Capabilities: Detect and interact with elements using visual appearance
State Management: Handle cookies, take screenshots, and manage browser sessions
Tab Management: Create, switch between, and close browser tabs
Customizable Configuration: Set API keys, Chrome options, and model parameters
Structured Responses: Receive JSON-formatted results from browser actions
This server integrates with the browser-use library and is designed primarily for development and testing environments.
Includes support for Google API integration as evidenced by the GOOGLE_API_KEY environment variable in the configuration.
Supports integration with Ollama for local execution of Large Language Models, providing an alternative to cloud-based AI providers.
Integrates with OpenAI's models for language and vision capabilities, allowing the browser automation system to leverage OpenAI's AI models for processing and generating content.
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 |
>=10.1.0 | Python Imaging Library (PIL) fork that adds image processing capabilities to your Python interpreter. | |
==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. | |
>=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. | |
>=0.4.1 | A framework that wraps FastAPI for building MCP (Model Context Protocol) servers. | |
>=1.7.2 | Library for structured output prompting and validation with OpenAI models. Enables extracting structured data from model responses. | |
>=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. | |
>=2.1.1 | LangChain integration for Google GenAI models, enabling the use of Google's generative AI capabilities within the LangChain framework. | |
>=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. | |
>=0.2.2 | Langchain integration for Ollama, enabling local execution of LLMs. | |
>=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). | |
>=1.0.1 | Reads key-value pairs from a
file and sets them as environment variables. Simplifies local development and configuration management. | |
>=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. | |
>=1.9.0 | Cross-platform Python module for copy and paste clipboard functions. | |
>=0.22.0 | ASGI web server implementation for Python. Used to serve the FastAPI application. |
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
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
"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.
Related MCP Servers
- AsecurityAlicenseAqualityAI-driven browser automation server that implements the Model Context Protocol to enable natural language control of web browsers for tasks like navigation, form filling, and visual interaction.Last updated -12MIT License
- -securityAlicense-qualityEmpowers AI agents to perform web browsing, automation, and scraping tasks with minimal supervision using natural language instructions and Selenium.Last updated -6Apache 2.0
- -securityFlicense-qualityEnables AI assistants to control a browser through a set of tools, allowing them to perform web automation tasks like navigation, typing, clicking, and taking screenshots.Last updated -