MCP Chat Support System
A comprehensive customer support platform featuring real-time messaging, knowledge base management, and a multi-tenant architecture with both React frontend and Node.js backend.
README
MCP Chat Support System
A comprehensive chat support system with React frontend and Node.js backend, featuring real-time messaging, knowledge base management, and multi-tenant architecture.
🚀 Features
Frontend (React + TypeScript)
- Modern UI/UX: Responsive design with mobile optimization
- Real-time Chat: WebSocket-based live messaging
- Authentication: Google OAuth integration
- Demo Mode: Interactive demo with simulated features
- Payment Integration: Stripe payment processing
- Video Calls: WebRTC video conferencing
- Knowledge Base: Searchable documentation system
- Admin Dashboard: Multi-tenant management interface
- Offline Support: Service worker for offline functionality
Backend (Node.js + TypeScript)
- RESTful API: Express.js server with TypeScript
- WebSocket Server: Real-time communication
- Database: SQLite with TypeORM
- Authentication: JWT token-based auth
- Multi-tenancy: Tenant isolation and management
- File Upload: Secure file handling
- Analytics: Usage tracking and reporting
- Widget System: Embeddable chat widgets
📁 Project Structure
project/
├── src/ # React frontend
│ ├── components/ # Reusable UI components
│ ├── pages/ # Page components
│ ├── contexts/ # React contexts
│ ├── hooks/ # Custom React hooks
│ ├── lib/ # Utility functions
│ └── types/ # TypeScript type definitions
├── server/ # Node.js backend
│ ├── src/
│ │ ├── routes/ # API route handlers
│ │ ├── middleware/ # Express middleware
│ │ ├── services/ # Business logic
│ │ └── db/ # Database models
│ ├── package.json
│ └── tsconfig.json
├── gemini-mcp-server/ # Gemini MCP integration
├── public/ # Static assets
└── docs/ # Documentation
🛠️ Tech Stack
Frontend
- React 18 with TypeScript
- Vite for build tooling
- Tailwind CSS for styling
- React Router for navigation
- Socket.io Client for real-time features
- Stripe for payments
- WebRTC for video calls
Backend
- Node.js with TypeScript
- Express.js framework
- Socket.io for WebSocket server
- SQLite database with TypeORM
- JWT for authentication
- Multer for file uploads
- Cors for cross-origin requests
🚀 Quick Start
Prerequisites
- Node.js 18+
- npm or yarn
- Git
Frontend Setup
# Install dependencies
npm install
# Start development server
npm run dev
# Build for production
npm run build
Backend Setup
# Navigate to server directory
cd server
# Install dependencies
npm install
# Copy environment variables
cp env.example .env
# Start development server
npm run dev
# Build for production
npm run build
Environment Variables
Create a .env file in the server directory:
# Server Configuration
PORT=3001
NODE_ENV=development
# Database
DATABASE_URL=sqlite:./database.sqlite
# JWT Secret
JWT_SECRET=your-jwt-secret-here
# Google OAuth
GOOGLE_CLIENT_ID=your-google-client-id
GOOGLE_CLIENT_SECRET=your-google-client-secret
# Stripe (for payments)
STRIPE_SECRET_KEY=your-stripe-secret-key
STRIPE_PUBLISHABLE_KEY=your-stripe-publishable-key
# File Upload
UPLOAD_DIR=uploads/
MAX_FILE_SIZE=5242880
📱 Features Overview
Chat Interface
- Real-time messaging with typing indicators
- File sharing and image uploads
- Message history and search
- Read receipts and delivery status
Knowledge Base
- Searchable documentation
- Category organization
- Rich text editing
- Version control
Admin Dashboard
- Multi-tenant management
- User analytics and reporting
- System configuration
- Widget customization
Widget System
- Embeddable chat widgets
- Customizable appearance
- Multi-language support
- Mobile responsive
🔧 Development
Code Style
- TypeScript for type safety
- ESLint for code linting
- Prettier for code formatting
- Husky for git hooks
Testing
# Run frontend tests
npm test
# Run backend tests
cd server && npm test
Database Migrations
cd server
npm run migration:generate
npm run migration:run
🚀 Deployment
Frontend (Vercel/Netlify)
npm run build
# Deploy the dist/ folder
Backend (Render/Railway)
cd server
npm run build
npm start
Docker Deployment
# Build and run with Docker Compose
docker-compose up -d
📊 API Documentation
Authentication Endpoints
POST /api/auth/login- User loginPOST /api/auth/register- User registrationPOST /api/auth/google- Google OAuthGET /api/auth/profile- Get user profile
Chat Endpoints
GET /api/chat/messages- Get chat historyPOST /api/chat/messages- Send messageGET /api/chat/rooms- Get chat rooms
Knowledge Base Endpoints
GET /api/knowledge- Get knowledge articlesPOST /api/knowledge- Create articlePUT /api/knowledge/:id- Update articleDELETE /api/knowledge/:id- Delete article
🤝 Contributing
- Fork the repository
- Create a feature branch (
git checkout -b feature/amazing-feature) - Commit your changes (
git commit -m 'Add amazing feature') - Push to the branch (
git push origin feature/amazing-feature) - Open a Pull Request
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
🆘 Support
For support and questions:
- Create an issue on GitHub
- Check the documentation in the
/docsfolder - Review the deployment guides
🔗 Links
Made with ❤️ by [Your Name]
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。