Windows ChatGPT MCP

Windows ChatGPT MCP

Enables Claude Desktop and VS Code Claude CLI to interact with ChatGPT on Windows systems through the MCP protocol. Provides seamless integration allowing users to leverage ChatGPT functionality within their Claude workflow with tools for sending messages, managing conversations, and accessing ChatGPT responses.

Category
Visit Server

README

Windows ChatGPT MCP Tool

⚠️ NOTICE: PRE-TESTING VERSION ⚠️
This tool is currently in development and has NOT been fully tested. Use at your own risk.
Comprehensive testing and validation are planned before the first stable release.

A Model Context Protocol (MCP) server that enables Claude Desktop and VS Code Claude CLI to interact with ChatGPT on Windows 11 systems.

Overview

This tool provides a bridge between Claude and ChatGPT on Windows, allowing you to leverage ChatGPT functionality within your Claude workflow through the MCP protocol. Get the best of both AI systems by combining Claude's analytical capabilities with ChatGPT's knowledge and conversational abilities.

Note: This is a Windows adaptation of the original claude-chatgpt-mcp tool for macOS, redesigned with Windows-native automation and enhanced features.

Key Features

  • 🔗 Seamless Integration - Connect Claude with ChatGPT through MCP protocol
  • 🪟 Windows Native - Optimized for Windows 11/10 with robust automation
  • 🛠️ Multiple Tools - Send messages, manage conversations, get debug info
  • 📊 Performance Monitoring - Built-in metrics and logging
  • 🔧 Easy Configuration - Works with Claude Desktop and VS Code
  • 🛡️ Error Handling - Comprehensive error recovery and retry logic

Quick Start

Prerequisites

  • ✅ Windows 11 (or Windows 10 1903+)
  • ✅ Python 3.8 or higher
  • ✅ ChatGPT desktop application
  • ✅ Claude Desktop OR VS Code with Claude CLI extension

Installation

Option 1: Pip Installation (Recommended)

pip install windows-chatgpt-mcp

Option 2: Standalone Executable

  1. Download windows-chatgpt-mcp.exe from the releases page
  2. Place the executable in your desired directory
  3. Run directly without Python installation required

Option 3: Development Installation

  1. Clone the repository:

    git clone https://github.com/kyungsuk-kim/windows-chatgpt-mcp.git
    cd windows-chatgpt-mcp
    
  2. Install dependencies:

    pip install -r requirements.txt
    
  3. Install the package:

    pip install -e .
    
  4. Verify installation:

    python -m src.mcp_server --test
    

Configuration

For Claude Desktop

Create or edit %APPDATA%\Claude\mcp.json:

{
  "mcpServers": {
    "windows-chatgpt": {
      "command": "python",
      "args": ["-m", "src.mcp_server"],
      "cwd": "C:/path/to/windows-chatgpt-mcp",
      "env": {
        "PYTHONPATH": "C:/path/to/windows-chatgpt-mcp/src",
        "WINDOWS_CHATGPT_MCP_LOG_LEVEL": "INFO"
      }
    }
  }
}

For VS Code Claude CLI

Add to your VS Code settings:

{
  "claude.mcpServers": {
    "windows-chatgpt": {
      "command": "python",
      "args": ["-m", "src.mcp_server"],
      "cwd": "C:/path/to/windows-chatgpt-mcp",
      "env": {
        "PYTHONPATH": "C:/path/to/windows-chatgpt-mcp/src"
      }
    }
  }
}

Usage

Basic Usage

Once configured, you can use ChatGPT through Claude:

You: Can you use the ChatGPT tool to ask: "What are the benefits of renewable energy?"

Claude: I'll send that question to ChatGPT for you.

[Uses send_message tool]

ChatGPT Response: Renewable energy offers numerous benefits including...

Claude: Based on ChatGPT's response, I can also add that...

Available Tools

Tool Description Usage
send_message Send a message to ChatGPT Ask Claude to send any question or request
get_conversation_history Get recent ChatGPT messages "Show me the last 5 ChatGPT messages"
reset_conversation Start fresh in ChatGPT "Reset the ChatGPT conversation"
get_debug_info Server diagnostics "Get debug info from the ChatGPT tool"

Common Use Cases

  • Research & Analysis - Get multiple AI perspectives on complex topics
  • Code Review - Have both AIs review your code for comprehensive feedback
  • Creative Writing - Collaborate between AIs for enhanced creativity
  • Problem Solving - Combine analytical approaches from both systems
  • Learning - Use both AIs for comprehensive educational content

Documentation

Configuration Examples

Development Setup

{
  "mcpServers": {
    "chatgpt-dev": {
      "command": "python",
      "args": ["-m", "src.mcp_server", "--debug"],
      "cwd": "C:/dev/windows-chatgpt-mcp",
      "env": {
        "WINDOWS_CHATGPT_MCP_LOG_LEVEL": "DEBUG",
        "WINDOWS_CHATGPT_MCP_TIMEOUT": "60"
      }
    }
  }
}

Production Setup

{
  "mcpServers": {
    "windows-chatgpt": {
      "command": "windows-chatgpt-mcp",
      "args": [],
      "env": {
        "WINDOWS_CHATGPT_MCP_LOG_LEVEL": "WARNING",
        "WINDOWS_CHATGPT_MCP_TIMEOUT": "30"
      }
    }
  }
}

Environment Variables

Variable Default Description
WINDOWS_CHATGPT_MCP_LOG_LEVEL INFO Logging verbosity
WINDOWS_CHATGPT_MCP_TIMEOUT 30 Response timeout (seconds)
WINDOWS_CHATGPT_MCP_DEBUG false Enable debug mode
WINDOWS_CHATGPT_MCP_WINDOW_TITLE ChatGPT Window detection pattern

Troubleshooting

Common Issues

ChatGPT not found:

  • Ensure ChatGPT desktop app is running and visible
  • Check window title matches expected pattern

Permission denied:

  • Run as administrator
  • Check Windows privacy settings for app control

Timeout errors:

  • Increase timeout value in configuration
  • Ensure stable internet connection

For detailed troubleshooting, see TROUBLESHOOTING.md

Performance

The tool includes comprehensive performance monitoring:

  • Response time tracking
  • Success/failure rates
  • Error categorization
  • Resource usage monitoring

Access performance data using the get_debug_info tool.

Security

  • Messages are processed locally through ChatGPT desktop app
  • No data is stored permanently by the MCP server
  • Follows Windows security best practices
  • Configurable logging levels to protect sensitive information

Contributing

We welcome contributions! Please read our Contributing Guidelines for detailed information.

Quick Start for Contributors

  1. Fork the repository
  2. Create a feature branch: git checkout -b feature/amazing-feature
  3. Make your changes and add tests
  4. Run the test suite: python run_tests.py
  5. Submit a pull request

Development Setup

# Clone your fork
git clone https://github.com/yourusername/windows-chatgpt-mcp.git
cd windows-chatgpt-mcp

# Create virtual environment
python -m venv venv
venv\Scripts\activate

# Install development dependencies
pip install -e .[dev]

# Install pre-commit hooks
pre-commit install

For detailed contributing guidelines, see CONTRIBUTING.md.

Support

Getting Help

Community

Professional Support

For enterprise support, custom integrations, or consulting services, please contact the maintainers through GitHub.

Distribution

Available Packages

The Windows ChatGPT MCP Tool is distributed in multiple formats:

  • Wheel Package: windows_chatgpt_mcp-1.0.0-py3-none-any.whl - Standard Python package
  • Source Distribution: windows_chatgpt_mcp-1.0.0.tar.gz - Source code archive
  • Standalone Executable: windows-chatgpt-mcp.exe - No Python installation required

Building from Source

To build your own distribution packages:

# Build all packages
python build_dist.py

# Build only wheel package
python build_dist.py --wheel-only

# Build only standalone executable
python build_dist.py --exe-only

For detailed build instructions, see DISTRIBUTION.md.

Roadmap

Version 1.1 (Planned)

  • [ ] Image and file attachment support
  • [ ] Enhanced error recovery mechanisms
  • [ ] Performance optimizations

Version 1.2 (Future)

  • [ ] Multiple ChatGPT account support
  • [ ] Enhanced conversation management
  • [ ] Additional automation features
  • [ ] Configuration GUI

Long-term Goals

  • [ ] Cross-platform support (macOS, Linux)
  • [ ] Plugin system for extensibility
  • [ ] Advanced AI workflow automation

License

MIT License - see LICENSE file for details.

Acknowledgments

This Windows ChatGPT MCP tool is based on the excellent work by syedazharmbnr1 and their claude-chatgpt-mcp project for macOS. We adapted their innovative approach to create a Windows-native version with enhanced automation capabilities.

Credits

  • Original Project: claude-chatgpt-mcp by syedazharmbnr1
  • Platform: Adapted from macOS to Windows with Windows-specific automation
  • MCP Protocol: Built on the Model Context Protocol (MCP) standard
  • Windows Integration: Uses Windows automation libraries for ChatGPT desktop app integration

Key Adaptations for Windows

  • Windows-native automation using pyautogui and pygetwindow
  • Windows-specific window management and detection
  • Enhanced error handling for Windows environment
  • Windows registry and file system integration
  • Comprehensive Windows installation and deployment support

Ready to get started? Follow the Setup Guide for detailed installation instructions.

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured