Ask ChatGPT

Provides a stdio MCP server that forwards prompts to ChatGPT for analysis, summarization, and reasoning.

python

6

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

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

You deploy a stdio MCP server that forwards prompts to OpenAI’s ChatGPT (GPT-4o) to perform advanced summarization, analysis, and reasoning. This server exposes a single tool that you can call from your LangGraph pipelines to analyze text, summarize configurations, or reason about complex content in real-time.

How to use

Connect the chatgpt MCP server to your client workflow. You send a request to the local stdio server with a tool call named ask_chatgpt and supply the content you want analyzed, summarized, or reasoned about. The server will forward that content to ChatGPT and return the results to your pipeline, enabling you to perform long-form analysis, compare configurations, or extract key insights from large documents.

How to install

Prerequisites you need on your machine or host: Python 3.x and Docker for running the container in isolation.

Option A: Run from Docker (recommended for quick start)

Build the container image

docker build -t ask-chatgpt-mcp .

Run the container with your OpenAI API key

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

Additional sections

Server tests and integration steps are provided to help you verify functionality and integrate with LangGraph pipelines.

Manual test you can perform locally to verify one-shot behavior is shown here. This demonstrates how to invoke the server to summarize or process content.

LangGraph integration involves connecting the MCP server as a tool within your pipeline so that you can trigger advanced reasoning on demand.

MCP server configuration is provided to ensure you can run the server with the proper environment variables and startup command.

Security: Do not commit API keys to source control. Use secure environment variables or secret managers for production deployments.

Configuration examples and environment details

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

Available tools

ask_chatgpt

Sends the provided text (content) to an external ChatGPT (gpt-4o) model for advanced reasoning or summarization.