Custommcp

🚀 Custom MCP (Model Context Protocol) and ChatGPT AI Template Project

This project combines a custom MCP (Model Control Protocol) with a ChatGPT AI template to provide an intelligent agent system that can integrate with Gmail and GitHub.

🚀 Quick Start

1. Follow the above instructions to start the MCP server and the ChatGPT AI template.
2. Open your browser and navigate to http://localhost:3000.
3. Click the "Start" button to enter the MCP console.
4. Enter and execute commands in the console.

✨ Features

• Gmail Integration: Read and analyze emails in your Gmail account.
• GitHub Integration: Interact with GitHub repositories to check issues, warnings, and other information.
• Intelligent Decision-making: Leverage OpenAI models to decide which tools to use and how to process information.
• Autonomous Operation: Navigate between different services autonomously to complete complex requests.
• Modern UI: A beautiful and responsive interface built with Next.js and Chakra UI.

💻 Usage Examples

• "Check if there are GitHub warnings in my Gmail."
• "Find dependency warnings in my repositories."
• "Summarize recent GitHub notifications."

📚 Documentation

Technology Stack

• Backend: FastAPI (Python)
• AI: OpenAI API
• External APIs: Gmail API, GitHub API
• Frontend: Next.js, React, Chakra UI

Project Structure

Custom-MCP/
├── src/                  # MCP server
│   ├── api/              # API endpoints
│   ├── services/         # Service integrations (Gmail, GitHub, OpenAI)
│   ├── models/           # Data models
│   ├── utils/            # Utility functions
│   ├── config/           # Configuration management
│   └── main.py           # Application entry point
├── chatgpt-ai-template/  # ChatGPT AI template
│   ├── app/              # Next.js application directory
│   ├── src/              # Source code
│   ├── public/           # Static assets
│   └── package.json      # Dependencies
├── .env                  # Environment variables (not in the repository)
├── .env.example          # Example environment variables
├── requirements.txt      # Python dependencies
├── start.sh              # Startup script
└── README.md             # This file

Setup Instructions

1. MCP Server Setup

1. Install Python dependencies:

   pip install -r requirements.txt
   

2. Set environment variables in the .env file (refer to .env.example).
3. Run the MCP server:

   python run.py
   

4. The MCP server will be available at http://localhost:8000.

2. ChatGPT AI Template Setup

1. Switch to the ChatGPT AI template directory:

   cd chatgpt-ai-template
   

2. Install Node.js dependencies:

   npm install
   

3. Run the development server:

   npm run dev
   

4. The ChatGPT AI template will be available at http://localhost:3000.

3. Quick Start (Both Servers Together)

For convenience, you can use the provided script to start both servers simultaneously:

./start.sh

This script will:

1. Start the MCP server in the background.
2. Wait for its initialization.
3. Start the ChatGPT AI template frontend.
4. Automatically stop the MCP server when you exit the frontend.

Configuration

You need to set the following API credentials:

• Gmail API (OAuth2)
• GitHub API (Personal Access Token)
• OpenAI API See the .env.example file for the required environment variables.

📄 License

This project is licensed under the MIT License.