Browser MCP Server
A Docker-based workspace providing headless Chrome browser with CDP proxy and noVNC interface for browser automation and monitoring.
README
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:
- Xvfb - Virtual display server
- Fluxbox - Lightweight window manager
- x11vnc + noVNC - Remote desktop access
- Chrome Browser - With undetected-chromedriver
- CDP Proxy Server - HTTP API for DevTools commands
- 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
- Mount extension directory as volume
- Update
init_chrome.pyto load extensions - Example configuration:
options.add_argument('--load-extension=/home/chrome/extensions/your-extension')
🧪 Testing the Setup
- Start the container
- Open noVNC at http://localhost:6080
- 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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.