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]
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.