cemigo114/gpt5-mcp-server

GPT-5 MCP Server

A Model Context Protocol server for GPT-5 interactions and Q&A workflows

Simple MCP server that provides tools for asking questions, continuing conversations, analyzing responses, and generating follow-ups with GPT-5.

Features

• 5 Core Tools - Ask questions, continue conversations, analyze responses
• Response Analysis - Quality scoring and feedback
• Follow-up Generation - Auto-generate related questions
• Response Comparison - Compare multiple responses
• Error Handling - Graceful API error handling with test mode

Quick Start

# Clone and install
git clone https://github.com/yourusername/gpt5-mcp-server
cd gpt5-mcp-server
npm install

# Set up environment
cp .env.example .env
# Add your OpenAI API key to .env

# Build and run
npm run build
npm start

Installation

1. Clone the repository:

   git clone https://github.com/yourusername/gpt5-mcp-server
   cd gpt5-mcp-server
   npm install
   

2. Set up environment:

   cp .env.example .env
   # Edit .env and add your OpenAI API key
   

3. Build and test:

   npm run build
   npm run test-server  # Test mode (no API key required)
   

Core Tools

1. ask_gpt5 - Ask GPT-5 Questions

{
  "question": "What is machine learning?",
  "context": "I'm a beginner learning about AI",
  "temperature": 0.7,
  "max_tokens": 500
}

2. continue_conversation - Multi-turn Conversations

{
  "messages": [
    {"role": "user", "content": "What is Python?"},
    {"role": "assistant", "content": "Python is a programming language..."},
    {"role": "user", "content": "How do I install it?"}
  ]
}

3. analyze_response - Analyze Response Quality

{
  "response": "Your GPT-5 response here...",
  "criteria": ["Accuracy", "Clarity", "Completeness"]
}

4. generate_followup_questions - Generate Follow-ups

{
  "original_question": "What is Python?",
  "response": "Python is a programming language...",
  "count": 3
}

5. compare_responses - Compare Multiple Responses

{
  "question": "What is the best programming language?",
  "responses": [
    {"id": "response_1", "content": "Python is the best because..."},
    {"id": "response_2", "content": "JavaScript is better because..."}
  ]
}

MCP Client Configuration

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "gpt5-qa": {
      "command": "node",
      "args": ["/path/to/gpt5-mcp-server/build/index.js"],
      "env": {
        "OPENAI_API_KEY": "your-api-key-here"
      }
    }
  }
}

Test Mode (No API Key Required)

{
  "mcpServers": {
    "gpt5-qa-test": {
      "command": "tsx",
      "args": ["./src/test-server.ts"],
      "cwd": "/path/to/gpt5-mcp-server"
    }
  }
}

Usage Examples

Once connected to your MCP client:

1. Ask a basic question:

   Use tool: ask_gpt5
   Arguments: {"question": "What is Python?", "temperature": 0.7}
   

2. Continue a conversation:

   Use tool: continue_conversation
   Arguments: {
     "messages": [
       {"role": "user", "content": "What is Python?"},
       {"role": "assistant", "content": "Python is a programming language..."},
       {"role": "user", "content": "How do I install it?"}
     ]
   }
   

3. Analyze a response:

   Use tool: analyze_response
   Arguments: {"response": "Your GPT response here", "criteria": ["Accuracy", "Clarity"]}
   

Development

Run in Development Mode

npm run dev  # Hot reload with tsx

Test Mode (No API Calls)

npm run test-server  # Uses mock responses

Build for Production

npm run build
npm start

Error Handling

The server includes graceful error handling:

• Quota Exceeded: Shows helpful error message with resolution steps
• API Errors: Detailed error information and troubleshooting
• Test Mode: Full functionality without API calls when quota is exceeded

License

MIT License - see for details.

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Test your changes
5. Submit a pull request