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
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@browser-use MCP server search for flights from New York to London next week"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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.
🧠 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
Related MCP server: Cloudflare Playwright MCP
Python 3.11 or higher
uv (fast Python package installer)
Chrome/Chromium browser
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"
}
}"browser-use": {
"command": "uv",
"args": [
"--directory",
"/path/to/mcp-browser-use",
"run",
"mcp-server-browser-use"
],
"env": {
...
}
}# Install dev dependencies
uv sync
# Run with debugger
npx @modelcontextprotocol/inspector uv --directory . run mcp-server-browser-useBrowser 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=true for screenshot analysis.
The server supports multiple LLM providers through environment variables. Here are the available options for MCP_MODEL_PROVIDER:
Provider | Value | Required Env Variables |
Anthropic |
|
|
OpenAI |
|
|
Azure OpenAI |
|
|
DeepSeek |
|
|
Gemini |
|
|
Mistral |
|
|
Ollama |
|
|
OpenRouter |
|
|
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_NAME
For Ollama models, additional context settings like num_ctx and num_predict are configurable
This project extends the browser-use/web-ui under MIT License. Special thanks to the original authors for their browser automation framework.
MIT - See LICENSE for details.
Handle run-browser-agent tool calls.
Inputs: task (required), add_infos.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'run_browser_agent' has a distinct purpose that cannot be confused with any other tool in this set.
The naming pattern cannot be inconsistent with only one tool. The tool name 'run_browser_agent' follows a clear verb_noun pattern, and there are no other tools to create naming conflicts or mixed conventions.
A single tool is generally too few for most server purposes, as it limits functionality and may not cover the domain adequately. For a browser automation server, one tool feels thin and restrictive compared to typical expectations of multiple actions like navigation, clicking, or form filling.
The tool surface is severely incomplete for browser automation. With only one tool to run an agent, there are obvious gaps in core operations such as navigating to URLs, interacting with page elements, extracting data, or managing browser sessions, which will likely cause agent failures in practical use.
Official Browserless MCP server: browser automation, scraping, screenshots and PDFs for AI agents.
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
Control a real browser from AI agents: navigate, click, type, screenshot, read the page.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
