UberEats MCP Server Enhanced
A production-ready MCP server for UberEats automation, featuring Redis-backed sessions, n8n integration, and enterprise-grade security, enabling login, item addition, address setting, and checkout.
README
UberEats MCP Server Enhanced
A modern, production-ready Model Context Protocol (MCP) server for UberEats automation built with TypeScript, Redis, and enterprise-grade security features.
🚀 Features
Core Functionality
- MCP Protocol Compliance: Native MCP server with tools, resources, and prompts
- Session Management: Redis-backed sessions with JWT authentication
- n8n Integration: Seamless workflow orchestration with circuit breakers
- Type Safety: Full TypeScript implementation with strict mode
- Security: Input validation, rate limiting, encryption, and audit logging
Performance & Scalability
- Horizontal Scaling: Stateless design with Redis session storage
- Circuit Breakers: Fault tolerance for external services
- Connection Pooling: Efficient resource management
- Caching: Redis-based caching for optimal performance
- Monitoring: Built-in health checks and metrics
Developer Experience
- Hot Reload: Development mode with automatic restarts
- Comprehensive Logging: Structured logging with pino
- Error Handling: Centralized error management
- Code Quality: ESLint, Prettier, and TypeScript strict mode
- Documentation: Complete API documentation and examples
📋 Prerequisites
- Node.js 20.0.0 or higher
- Redis 7.0 or higher
- n8n workflow automation platform
- Docker (optional, for containerized deployment)
🛠 Installation
Option 1: Local Development
# Clone the repository
cd ubereats_mcp_server_enhanced
# Install dependencies
npm install
# Copy environment configuration
cp .env.example .env
# Edit configuration
nano .env
# Build the project
npm run build
# Start Redis (if not running)
redis-server
# Start the server
npm start
Option 2: Docker Deployment
# Copy environment configuration
cp .env.example .env
# Edit configuration for production
nano .env
# Start all services
docker-compose up -d
# View logs
docker-compose logs -f ubereats-mcp
⚙️ Configuration
Environment Variables
Create a .env file based on .env.example:
# Security (REQUIRED for production)
JWT_SECRET=your-super-secure-jwt-secret-key-change-in-production
SESSION_SECRET=your-session-secret-key-change-in-production
ENCRYPTION_KEY=your-32-character-encryption-key-change-this
# Redis Configuration
REDIS_HOST=localhost
REDIS_PORT=6379
REDIS_PASSWORD=
REDIS_DB=0
# n8n Integration
N8N_BASE_URL=http://localhost:5678
N8N_API_KEY=
# Server Configuration
NODE_ENV=production
PORT=5001
LOG_LEVEL=info
MCP Client Configuration
Add to your Claude Desktop configuration:
{
"mcpServers": {
"ubereats": {
"command": "node",
"args": ["/path/to/ubereats_mcp_server_enhanced/dist/index.js"],
"env": {
"NODE_ENV": "production"
}
}
}
}
🔧 Usage
MCP Tools
Login Tool
{
"name": "ubereats_login",
"arguments": {
"username": "user@example.com",
"password": "password",
"manualMode": false
}
}
Add Items Tool
{
"name": "ubereats_add_items",
"arguments": {
"sessionId": "session-uuid",
"restaurantName": "McDonald's",
"items": [
{
"name": "Big Mac",
"quantity": 2,
"options": {
"size": "large",
"extras": ["cheese"]
}
}
]
}
}
Set Address Tool
{
"name": "ubereats_set_address",
"arguments": {
"sessionId": "session-uuid",
"address": {
"street": "123 Main St",
"city": "Anytown",
"state": "CA",
"zipCode": "90210"
}
}
}
Checkout Tool
{
"name": "ubereats_checkout",
"arguments": {
"sessionId": "session-uuid",
"paymentMethodId": "saved_card_123",
"tipAmount": 5.00
}
}
MCP Resources
Health Check
URI: ubereats://health
Returns server health status, system metrics, and service availability.
Session Information
URI: ubereats://sessions
Returns information about active sessions and session counts.
Prompts
Quick Order
{
"name": "quick_order",
"arguments": {
"restaurant": "Pizza Hut",
"items": "Large pepperoni pizza, 2 liter Coke",
"address": "123 Main St, Anytown, CA 90210"
}
}
🏗 Architecture
System Overview
┌─────────────────┐ ┌─────────────────┐ ┌─────────────────┐
│ MCP Client │◄──►│ MCP Server │◄──►│ Redis Cache │
│ (Claude) │ │ (TypeScript) │ │ (Sessions) │
└─────────────────┘ └─────────────────┘ └─────────────────┘
│
▼
┌─────────────────┐ ┌─────────────────┐
│ n8n Server │◄──►│ Playwright │
│ (Workflows) │ │ (Browser) │
└─────────────────┘ └─────────────────┘
Component Details
- MCP Server: TypeScript server implementing MCP protocol
- Session Service: Redis-backed session management with JWT
- n8n Service: Workflow orchestration with circuit breakers
- Tools: MCP tools for UberEats operations
- Resources: Information endpoints for monitoring
- Prompts: Pre-defined interaction templates
🔒 Security Features
Authentication & Authorization
- JWT token-based session management
- Session validation on all protected operations
- Secure session storage with Redis TTL
Input Validation
- Zod schema validation for all inputs
- XSS protection and sanitization
- SQL injection prevention (Redis NoSQL)
Rate Limiting
- Per-endpoint rate limiting
- Global rate limiting
- Configurable limits and windows
Data Protection
- AES-256 encryption for sensitive data
- Secure cookie handling
- Password exclusion from logs and storage
Monitoring & Auditing
- Comprehensive audit logging
- Security event tracking
- Performance monitoring
📊 Monitoring & Observability
Health Checks
# Check server health
curl http://localhost:5001/health
# Docker health check
docker-compose ps
Logging
- Structured JSON logging with pino
- Configurable log levels
- Request/response logging with sensitive data redaction
Metrics
- Redis connection health
- n8n service availability
- Circuit breaker status
- Session statistics
🧪 Testing
# Run tests
npm test
# Run tests with coverage
npm run test:coverage
# Run tests in watch mode
npm run test:watch
# Lint code
npm run lint
# Format code
npm run format
# Type check
npm run type-check
MCP Inspector
The MCP Inspector is a powerful debugging tool that allows you to test and interact with your MCP server directly. It provides a web-based interface to:
- Test MCP tools with custom parameters
- View available resources and prompts
- Monitor server responses and errors
- Validate MCP protocol compliance
Running the MCP Inspector
# Build the project first
npm run build
# Start the MCP Inspector
npm run inspector
# Or run directly with npx
npx @modelcontextprotocol/inspector dist/index.js
This will start a web interface (typically at http://localhost:5173) where you can:
- Test Tools: Call any registered tool (login, add_items, set_address, checkout) with custom parameters
- View Resources: Access health check and session information resources
- Test Prompts: Try the quick_order and reorder prompts with different parameters
- Debug Issues: See detailed request/response logs and error messages
Inspector Usage Tips
- Environment Setup: Ensure Redis and n8n are running before testing tools
- Tool Testing: Start with the login tool to establish a session, then test other tools
- Error Debugging: Check the inspector console for detailed error messages
- Schema Validation: The inspector validates input schemas automatically
The inspector is essential for development and debugging, allowing you to test the MCP server independently of Claude Code integration.
🚀 Deployment
Production Deployment
- Environment Setup
# Set production environment variables
export NODE_ENV=production
export JWT_SECRET="your-production-jwt-secret"
export SESSION_SECRET="your-production-session-secret"
export ENCRYPTION_KEY="your-production-encryption-key"
- Database Setup
# Start Redis
docker run -d --name redis -p 6379:6379 redis:7-alpine
# Or use managed Redis (AWS ElastiCache, etc.)
- Application Deployment
# Build application
npm run build
# Start with PM2 (recommended)
pm2 start dist/index.js --name ubereats-mcp
# Or use Docker
docker-compose up -d
Kubernetes Deployment
See k8s/ directory for Kubernetes manifests (coming soon).
🐛 Troubleshooting
Common Issues
Server Won't Start
# Check Node.js version
node --version # Should be >= 20.0.0
# Check environment variables
npm run check-env
# Check Redis connection
redis-cli ping
Authentication Errors
# Verify JWT secret is set
echo $JWT_SECRET
# Check session in Redis
redis-cli get "ubereats:session:your-session-id"
n8n Integration Issues
# Test n8n connectivity
curl http://localhost:5678/health
# Check circuit breaker status
curl http://localhost:5001/api/circuit-breakers
Debug Mode
# Enable debug logging
export LOG_LEVEL=debug
export ENABLE_DEBUG=true
# Start server
npm run dev
🤝 Contributing
- Fork the repository
- Create a feature branch:
git checkout -b feature/amazing-feature - Commit changes:
git commit -m 'Add amazing feature' - Push to branch:
git push origin feature/amazing-feature - Open a Pull Request
Development Guidelines
- Follow TypeScript strict mode
- Write tests for new features
- Update documentation
- Use conventional commits
- Ensure code passes linting
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🙏 Acknowledgments
- Model Context Protocol by Anthropic
- n8n for workflow automation
- Redis for session management
- TypeScript for type safety
📞 Support
- Create an issue for bug reports
- Use discussions for questions
- Check the troubleshooting guide first
Note: This is an enhanced version of the original Flask-based UberEats MCP server, rebuilt with modern technologies and enterprise-grade features.
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。