MCP Deepseek Demo

🚀 MCP DeepSeek Demo Project

The MCP DeepSeek Demo Project is a client application based on the Model Context Protocol (MCP) for interacting with DeepSeek AI models. It demonstrates how to integrate the MCP protocol with the DeepSeek API to achieve tool invocation and real-time communication.

🚀 Quick Start

Prerequisites

• Node.js 16+ and npm/yarn/pnpm
• DeepSeek API key

Installation

1. Clone the repository

git clone https://github.com/yourusername/mcp-deepseek-demo.git
cd mcp-deepseek-demo

2. Install dependencies

pnpm install

3. Configure environment variables Create a .env file in the mcp-client directory and add the following configuration:

# MCP server configuration
MCP_SERVER_URL=http://localhost:8083/sse

# AI provider configuration
DEEPSEEK_API_KEY=sk-...
DEEPSEEK_API_URL=https://api.deepseek.com/v1/chat/completions

# Default AI model to use
DEFAULT_MODEL=deepseek-chat

Create a .env file in the mcp-sse-server directory and add the following configuration:

PORT=8083

✨ Features

• A modern Chinese user interface
• Real-time chat interaction with the AI assistant
• Support for multiple tool invocations, such as product query and inventory management
• Real-time communication based on SSE
• Automatic reconnection mechanism
• Responsive design for different devices

📦 Installation

The installation steps are described in the "Quick Start" section above.

💻 Usage Examples

Basic Usage

1. Start the service

cd mcp-sse-server && npm start

2. Run the client

cd mcp-client && npm run dev

📚 Documentation

Project Structure

mcp-deepseek-demo/
├── mcp-client/                # Front-end application, based on Next.js to implement the user interface and API integration
│   ├── package.json          # Project dependency management file
│   └── .env                  # Environment variable configuration file
├── mcp-sse-server/           # Back-end service, based on Node.js and SSE to implement tool invocation functions
│   ├── package.json         # Project dependency management file
│   └── .env                 # Environment variable configuration file
└── README.md                # Project documentation

Tool List

• mcp-client: Provides a user interface for interacting with the DeepSeek AI model, supporting the following functions:
  • Real-time chat
  • File upload and download
  • System file operations
• mcp-sse-server: Provides the following tool interfaces:
  • File management: Supports file upload, download, and deletion
  • System command execution: Supports executing system commands on the server side

Technology Stack

• Front-end: Next.js, React, TypeScript, Tailwind CSS
• Back-end: Node.js, TypeScript
• Communication: Server-Sent Events (SSE)
• API: DeepSeek API, Model Context Protocol (MCP)

🤝 Contribution Guidelines

Contributions and issue reports are welcome! Please follow these steps:

1. Fork the repository
2. Create your feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add some amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📄 License

MIT LICENSE