Coder Chrome Automation and MCP

Coder Chrome Automation and MCP

Provision a Coder workspace with headless Chrome browser, CDP proxy, and noVNC interface for browser automation and monitoring.

🚀 Features

• Preconfigured Chrome with undetected-chromedriver
• CDP (Chrome DevTools Protocol) HTTP proxy API
• noVNC remote desktop access
• Randomized browser fingerprint generation
• Persistent user profile storage
• Supervisor process management

📦 Getting Started

1. Build the Docker image

docker build -t coder-chrome .

2. Run the container

docker run -d \
  -p 6080:6080 \
  -p 9223:9223 \
  --name chrome-workspace \
  coder-chrome

3. Access the workspace

• noVNC: http://localhost:6080
• CDP Proxy: http://localhost:9223
• Chrome Profile: /home/chrome/profile (persistent volume)

🧱 Architecture

The workspace includes:

1. Xvfb - Virtual display server
2. Fluxbox - Lightweight window manager
3. x11vnc + noVNC - Remote desktop access
4. Chrome Browser - With undetected-chromedriver
5. CDP Proxy Server - HTTP API for DevTools commands
6. Supervisor - Process management

🛠️ Example API Requests

1. Get browser fingerprint

curl -X POST http://localhost:9223 \
  -H "Content-Type: application/json" \
  -d '{"method": "Browser.getFingerprint"}'

2. Set network conditions

curl -X POST http://localhost:9223 \
  -H "Content-Type: application/json" \
  -d '{
    "method": "Network.emulateNetworkConditions",
    "params": {
      "offline": false,
      "latency": 50,
      "downloadThroughput": 1024000,
      "uploadThroughput": 512000
    }
  }'

3. Get page load metrics

curl -X POST http://localhost:9223 \
  -H "Content-Type: application/json" \
  -d '{"method": "Performance.getMetrics"}'

🧪 Advanced Usage

Custom User-Agent

curl -X POST http://localhost:9223 \
  -H "Content-Type: application/json" \
  -d '{
    "method": "Network.setUserAgentOverride",
    "params": {
      "userAgent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/117.0.0.0 Safari/537.36"
    }
  }'

Add browser extensions

1. Mount extension directory as volume
2. Update init_chrome.py to load extensions
3. Example configuration:

options.add_argument('--load-extension=/home/chrome/extensions/your-extension')

🧪 Testing the Setup

1. Start the container
2. Open noVNC at http://localhost:6080
3. Verify Chrome is running with:

docker exec -it chrome-workspace ps aux

🧼 Maintenance

Update dependencies

docker build --no-cache -t coder-chrome .

Clean up old containers

docker rm -f chrome-workspace