Web Proxy MCP Server
Intelligent HTTP/HTTPS proxy server with MCP integration for automated traffic monitoring, analysis, and browser setup.
README
Web Proxy MCP Server
Intelligent HTTP/HTTPS proxy server with Model Context Protocol (MCP) integration for automated traffic monitoring, analysis, and browser setup.
🌟 Features
Core Proxy Capabilities
- Selective Proxying: Only monitor specific domains while allowing direct access to others
- HTTP/HTTPS Support: Full support for HTTP requests and HTTPS tunneling via CONNECT
- PAC File Generation: Automatic Proxy Auto-Configuration file generation
- Traffic Capture: Detailed request/response logging with optional header/body capture
MCP Integration
- 16 MCP Tools: Complete automation via Model Context Protocol
- Dynamic Configuration: Add/remove monitored domains at runtime
- Real-time Analysis: Traffic pattern analysis and performance metrics
- HAR Export: Standard HTTP Archive format for external analysis
Browser Setup Automation
- Multi-Browser Support: Chrome, Firefox, cURL, and system-wide proxy setup
- Script Generation: Automated setup script generation for different platforms
- One-Click Configuration: Simple browser proxy configuration
🚀 Quick Start
Installation
cd /home/solar/docker-appliance/mcp-servers/web-proxy-mcp
npm install
Basic Usage
# Start the proxy server
npm start
# Or run directly
node index.js
Add to VS Code MCP Configuration
Add to your VS Code mcp.json:
{
"mcpServers": {
"web-proxy-mcp": {
"command": "node",
"args": ["/home/solar/docker-appliance/mcp-servers/web-proxy-mcp/index.js"],
"env": {}
}
}
}
🔧 MCP Tools
Target Management
proxy_add_target: Add domains to monitorproxy_remove_target: Remove domains from monitoringproxy_list_targets: List all configured targetsproxy_update_target: Update target configuration
Server Control
proxy_start_server: Start the proxy serverproxy_stop_server: Stop the proxy serverproxy_server_status: Get server status and statistics
Browser Setup
proxy_generate_setup: Generate browser setup scriptsproxy_get_pac_file: Get PAC file content
Traffic Analysis
proxy_get_traffic_log: View captured trafficproxy_export_har: Export traffic as HAR fileproxy_clear_traffic_log: Clear traffic logsproxy_analyze_traffic: Analyze traffic patterns
Configuration
proxy_import_config: Import configuration from fileproxy_export_config: Export configuration to file
Advanced Analysis
proxy_analyze_traffic: Traffic pattern analysisproxy_get_performance_metrics: Performance monitoring
📊 Usage Examples
1. Monitor Specific API
// Add target domain
await mcp.callTool('proxy_add_target', {
domain: 'api.example.com',
description: 'Main API endpoint',
captureHeaders: true,
captureBody: true
});
// Start proxy server
await mcp.callTool('proxy_start_server', {
port: 8080,
host: 'localhost'
});
// Generate browser setup
await mcp.callTool('proxy_generate_setup', {
proxyHost: 'localhost',
proxyPort: 8080
});
2. Traffic Analysis
// Get traffic log
const traffic = await mcp.callTool('proxy_get_traffic_log', {
domain: 'api.example.com',
limit: 50
});
// Analyze patterns
const analysis = await mcp.callTool('proxy_analyze_traffic', {
domain: 'api.example.com',
timeframe: '24h',
groupBy: 'method'
});
// Export HAR file
await mcp.callTool('proxy_export_har', {
domain: 'api.example.com',
filename: 'api-traffic-analysis'
});
3. Browser Configuration
// Get PAC file for manual setup
const pac = await mcp.callTool('proxy_get_pac_file', {
proxyHost: 'localhost',
proxyPort: 8080
});
// Generate all setup scripts
const setup = await mcp.callTool('proxy_generate_setup', {
browsers: ['chrome', 'firefox', 'system']
});
🔄 Workflow Integration
Development Debugging
- Add your development domains to the proxy
- Start the proxy server
- Configure your browser to use the proxy
- Monitor API calls and responses in real-time
- Export traffic logs for analysis
API Testing
- Configure proxy for your test endpoints
- Run automated tests through the proxy
- Capture all HTTP traffic automatically
- Analyze response times and error patterns
- Export detailed HAR files for reporting
Security Analysis
- Monitor specific domains for security testing
- Capture detailed request/response headers
- Analyze traffic patterns for anomalies
- Export logs for security review
📁 Project Structure
web-proxy-mcp/
├── index.js # Main MCP server entry point
├── package.json # Node.js dependencies
├── src/
│ ├── proxy/
│ │ ├── target-manager.js # Domain target management
│ │ └── proxy-server.js # HTTP/HTTPS proxy server
│ ├── traffic/
│ │ └── traffic-analyzer.js # Traffic capture and analysis
│ ├── setup/
│ │ └── browser-setup.js # Browser configuration scripts
│ └── tools/
│ ├── tool-definitions.js # MCP tool schemas
│ └── tool-handlers.js # MCP tool implementations
├── data/
│ ├── targets.json # Persistent target configuration
│ └── traffic-log.json # Persistent traffic logs
└── setup-scripts/ # Generated browser setup scripts
├── chrome-proxy-setup.sh
├── firefox-proxy-setup.sh
├── curl-proxy-setup.sh
├── system-proxy-setup.sh
└── proxy.pac
⚙️ Configuration
Target Configuration
Targets are stored in data/targets.json:
{
"httpbin.org": {
"domain": "httpbin.org",
"description": "HTTP testing service",
"enabled": true,
"captureHeaders": true,
"captureBody": false,
"createdAt": "2025-01-11T10:00:00.000Z"
}
}
Traffic Analysis
- Max Entries: 5,000 traffic entries (configurable)
- Persistence: Automatic save/load from
data/traffic-log.json - HAR Export: Standard HTTP Archive format
- Real-time Metrics: Performance and usage statistics
Proxy Server
- Default Port: 8080 (configurable)
- PAC File: Automatic generation at
/proxy.pac - Protocol Support: HTTP and HTTPS (via CONNECT tunneling)
- Performance Monitoring: Built-in metrics collection
🔒 Security Considerations
- Local Only: Default configuration binds to localhost only
- Selective Monitoring: Only configured domains are proxied
- No Body Capture by Default: Sensitive data protection
- Configurable Headers: Optional header capture for debugging
🤝 Integration with Other Tools
VS Code Workflow
- Add to MCP configuration in VS Code
- Use AI assistant to manage proxy configuration
- Automate traffic analysis through AI commands
- Generate reports and documentation automatically
Development Workflow
- Monitor local development APIs
- Test staging environment interactions
- Debug production API calls (headers only)
- Performance testing and analysis
📈 Performance
- Minimal Overhead: Only proxied domains incur processing cost
- Efficient Storage: Configurable traffic log retention
- Background Processing: Non-blocking traffic capture
- Memory Management: Automatic cleanup of old entries
🛠️ Advanced Features
Custom PAC Generation
The proxy generates intelligent PAC files that only route monitored domains through the proxy, maintaining normal browsing speed for other sites.
Traffic Pattern Analysis
Built-in analysis tools help identify:
- API usage patterns
- Response time trends
- Error rate monitoring
- Domain-specific metrics
Multi-Browser Support
Automated setup scripts for:
- Chrome (with security flags for testing)
- Firefox (with custom profile)
- System-wide proxy (Linux/macOS)
- Command-line tools (cURL)
🔧 Troubleshooting
Common Issues
- Port in use: Change the proxy port in server configuration
- Browser not using proxy: Verify PAC file URL or manual proxy settings
- HTTPS issues: Check certificate handling in browser settings
- No traffic captured: Ensure domains are added to target list
Debug Mode
Run with debug logging:
DEBUG=web-proxy-mcp node index.js
Logs Location
- Server logs: Console output
- Traffic logs:
data/traffic-log.json - Target config:
data/targets.json
📝 License
This project is part of the Docker Appliance MCP server collection and follows the same licensing terms.
🤖 AI Assistant Integration
This proxy is designed to work seamlessly with AI assistants through MCP:
- Natural Language Control: "Start monitoring api.example.com"
- Automated Analysis: "Analyze the last hour of API traffic"
- Report Generation: "Export traffic data for the payment API"
- Configuration Management: "Set up Chrome to use the proxy"
The MCP integration makes this proxy particularly powerful for AI-assisted development and debugging workflows.
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.