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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。