A Model Context Protocol (MCP) server for browser automation using Playwright, deployed on Google Cloud Run. This project provides browser automation capabilities through both REST API and MCP protocol endpoints.

• 🌐 Browser Automation Tools:

  • Navigate to URLs
  • Take screenshots
  • Click elements
  • Fill form fields
  • Read page content

• 🔧 Dual Protocol Support:

  • REST API endpoints for direct HTTP access
  • MCP protocol for AI agent integration

• ☁️ Cloud-Native Design:

  • Deployed on Google Cloud Run
  • Docker containerized
  • Auto-scaling and serverless

• 🔒 Security Features:

  • Domain allowlist
  • Google Cloud identity token authentication
  • Audit logging

1. Clone the repository:

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

2. Set up Python environment:

python3 -m venv .venv source .venv/bin/activate # On Windows: .venv\Scripts\activate pip install -r requirements.txt playwright install chromium

3. Run the MCP server:

uvicorn app:app --host 0.0.0.0 --port 8080

4. Test with the chat interface:

# In another terminal python3 -m http.server 8090 # Open http://localhost:8090/chat_interface_v2.html

# Take a screenshot curl -X POST http://localhost:8080/mcp/tools/screenshot \ -H "Content-Type: application/json" \ -d '{"url": "https://example.com", "full_page": false}' # Navigate to a URL curl -X POST http://localhost:8080/mcp/tools/navigate \ -H "Content-Type: application/json" \ -d '{"url": "https://github.com"}' # Read page content curl -X POST http://localhost:8080/mcp/tools/read \ -H "Content-Type: application/json" \ -d '{"url": "https://example.com", "selector": "h1"}'

import asyncio import aiohttp async def take_screenshot(): async with aiohttp.ClientSession() as session: async with session.post( "http://localhost:8080/mcp/tools/screenshot", json={"url": "https://github.com", "full_page": False} ) as resp: result = await resp.json() # result contains base64 encoded screenshot asyncio.run(take_screenshot())

1. Build and deploy:

gcloud builds submit --config cloudbuild.yaml

2. Environment variables:
   • ALLOWED_DOMAINS: Comma-separated list of allowed domains
   • LOG_LEVEL: Logging level (default: INFO)

browser-use-mcp/ ├── app.py # Main FastAPI application ├── mcp_tools.py # Browser automation tool implementations ├── browser_manager.py # Centralized browser lifecycle management ├── security_middleware.py # Google Cloud logging integration ├── chat_interface_v2.html # Web-based chat interface ├── requirements.txt # Python dependencies ├── Dockerfile # Container configuration ├── cloudbuild.yaml # CI/CD pipeline └── agents/ # ADK agent configurations 

Capture a screenshot of a webpage.

{ "url": "https://example.com", "full_page": false }

Navigate to a URL and return page information.

{ "url": "https://example.com" }

Click an element on the page.

{ "url": "https://example.com", "selector": "button#submit", "return_screenshot": false }

Fill a form field with text.

{ "url": "https://example.com", "selector": "input[name='email']", "text": "user@example.com", "return_screenshot": false }

Extract text content from the page.

{ "url": "https://example.com", "selector": "article" }

python test_all_tools.py

docker build -t browser-use-mcp . docker run -p 8080:8080 browser-use-mcp

1. CORS errors in browser: The server includes CORS middleware. Make sure you're accessing from allowed origins.

2. Playwright browser issues: Ensure Chromium is installed:

   playwright install chromium

3. Port already in use: Check for running processes:

   lsof -i :8080

1. Fork the repository
2. Create a feature branch
3. Commit your changes
4. Push to the branch
5. Create a Pull Request

This project is licensed under the MIT License - see the LICENSE file for details.

• Built with FastAPI
• Browser automation powered by Playwright
• MCP protocol implementation using FastMCP
• Deployed on Google Cloud Run