ChatGPT (OpenAI GPT-4o) MCP server

The Ask ChatGPT MCP Server is a Model Context Protocol (stdio) server that forwards prompts to OpenAI's ChatGPT (GPT-4o). It provides a tool for LangGraph-based assistants to access an external LLM for advanced summarization, analysis, and reasoning capabilities.

Installation

Docker Installation

The easiest way to get started is by using Docker:

docker build -t ask-chatgpt-mcp .
docker run -e OPENAI_API_KEY=your-openai-key -i ask-chatgpt-mcp

Environment Setup

The server requires an OpenAI API key to function. You can provide this in several ways:

1. Create a .env file (automatically loaded with python-dotenv):

OPENAI_API_KEY=your-openai-key

2. Export the key manually:

export OPENAI_API_KEY=your-openai-key

Dependencies

If not using Docker, you'll need to install these dependencies:

• openai
• requests
• python-dotenv

Usage

Available Tool

The server exposes a single tool called ask_chatgpt:

{
  "name": "ask_chatgpt",
  "description": "Sends the provided text ('content') to an external ChatGPT (gpt-4o) model for advanced reasoning or summarization.",
  "parameters": {
    "type": "object",
    "properties": {
      "content": {
        "type": "string",
        "description": "The text to analyze, summarize, compare, or reason about."
      }
    },
    "required": ["content"]
  }
}

Testing Locally

You can test the server locally using a one-shot request:

echo '{"method":"tools/call","params":{"name":"ask_chatgpt","arguments":{"content":"Summarize this config..."}}}' | \
  OPENAI_API_KEY=your-openai-key python3 server.py --oneshot

Integrating with LangGraph

To connect this MCP server to your LangGraph pipeline, configure it like this:

("chatgpt-mcp", ["python3", "server.py", "--oneshot"], "tools/discover", "tools/call")

MCP Server Configuration

Here's how to configure the server using an mcpServers JSON config:

{
  "mcpServers": {
    "chatgpt": {
      "command": "python3",
      "args": [
        "server.py",
        "--oneshot"
      ],
      "env": {
        "OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
      }
    }
  }
}

Usage Scenarios

This tool is particularly useful when your assistant needs to:

• Summarize long documents
• Analyze configuration files
• Compare options
• Perform advanced natural language reasoning

Security Considerations

• Never commit .env files or API keys
• Store secrets in secure environment variables or secret managers

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.