-
securityF
license-
qualityA Model Control Protocol server that enables AI assistants to control a browser through tools for web automation tasks like navigation, typing, clicking, and taking screenshots.
Last updated -
Connects to Google's Gemini API using the Google API key for AI-driven browser automation tasks
Provides integration with Ollama's local LLM hosting service, supporting customizable context settings and model parameters for browser automation
Integrates with OpenAI's API for LLM functionality, enabling AI-powered browser control with customizable parameters
browser-use MCP server
Project Note: This MCP server implementation builds upon the browser-use/web-ui foundation. Core browser automation logic and configuration patterns are adapted from the original project.
AI-driven browser automation server implementing the Model Context Protocol (MCP) for natural language browser control.
Features
🧠 MCP Integration - Full protocol implementation for AI agent communication
🌐 Browser Automation - Page navigation, form filling, and element interaction
👁️ Visual Understanding - Screenshot analysis and vision-based interactions
🔄 State Persistence - Maintain browser sessions between tasks
🔌 Multi-LLM Support - OpenAI, Anthropic, Azure, DeepSeek integration
Quick Start
Prerequisites
Python 3.11 or higher
uv (fast Python package installer)
Chrome/Chromium browser
Installation
Claude Desktop
On MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
"mcpServers": {
"browser-use": {
"command": "uvx",
"args": [
"mcp-server-browser-use",
],
"env": {
"OPENROUTER_API_KEY": "",
"OPENROUTER_ENDPOINT": "https://openrouter.ai/api/v1",
"OPENAI_ENDPOINT": "https://api.openai.com/v1",
"OPENAI_API_KEY": "",
"ANTHROPIC_ENDPOINT": "https://api.anthropic.com",
"ANTHROPIC_API_KEY": "",
"GOOGLE_API_KEY": "",
"AZURE_OPENAI_ENDPOINT": "",
"AZURE_OPENAI_API_KEY": "",
"DEEPSEEK_ENDPOINT": "https://api.deepseek.com",
"DEEPSEEK_API_KEY": "",
"MISTRAL_API_KEY": "",
"MISTRAL_ENDPOINT": "https://api.mistral.ai/v1",
"OLLAMA_ENDPOINT": "http://localhost:11434",
"ANONYMIZED_TELEMETRY": "true",
"BROWSER_USE_LOGGING_LEVEL": "info",
"CHROME_PATH": "",
"CHROME_USER_DATA": "",
"CHROME_DEBUGGING_PORT": "9222",
"CHROME_DEBUGGING_HOST": "localhost",
"CHROME_PERSISTENT_SESSION": "false",
"BROWSER_HEADLESS": "false",
"BROWSER_DISABLE_SECURITY": "false",
"BROWSER_WINDOW_WIDTH": "1280",
"BROWSER_WINDOW_HEIGHT": "720",
"BROWSER_TRACE_PATH": "trace.json",
"BROWSER_RECORDING_PATH": "recording.mp4",
"RESOLUTION": "1920x1080x24",
"RESOLUTION_WIDTH": "1920",
"RESOLUTION_HEIGHT": "1080",
"VNC_PASSWORD": "youvncpassword",
"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"
}
}
Local Development
"browser-use": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-browser-use",
"run",
"mcp-server-browser-use"
],
"env": {
...
}
}
Development
# Install dev dependencies
uv sync
# Run with debugger
npx @modelcontextprotocol/inspector uv --directory . run mcp-server-browser-use
Troubleshooting
Browser Conflicts: Close all Chrome instances before starting.
API Errors: Verify API keys in environment variables match your LLM provider.
Vision Support: Ensure
MCP_USE_VISION=truefor screenshot analysis.
Provider Configuration
The server supports multiple LLM providers through environment variables. Here are the available options for MCP_MODEL_PROVIDER:
Provider | Value | Required Env Variables |
Anthropic |
|
(optional) |
OpenAI |
|
(optional) |
Azure OpenAI |
|
|
DeepSeek |
|
(optional) |
Gemini |
|
|
Mistral |
|
(optional) |
Ollama |
|
(optional, defaults to localhost:11434) |
OpenRouter |
|
(optional) |
Notes:
For endpoints marked as optional, default values will be used if not specified
Temperature can be configured using
MCP_TEMPERATURE(default: 0.3)Model can be specified using
MCP_MODEL_NAMEFor Ollama models, additional context settings like
num_ctxandnum_predictare configurable
Credits
This project extends the browser-use/web-ui under MIT License. Special thanks to the original authors for their browser automation framework.
License
MIT - See LICENSE for details.
local-only server
The server can only run on the client's local machine because it depends on local resources.
Tools
AI-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.
Related MCP Servers
- -securityFlicense-qualityA Model Control Protocol server that enables AI assistants to control a browser through tools for web automation tasks like navigation, typing, clicking, and taking screenshots.Last updated -
- -securityFlicense-qualityA Model Control Protocol server that enables AI assistants to control a browser, allowing them to perform web automation tasks like navigation, typing, clicking, and taking screenshots.Last updated -
- -securityAlicense-qualityA Model Context Protocol server that enables AI assistants to control web browsers programmatically, allowing for web automation through natural language commands.