chatgpt-mcp
chatgpt-mcp is an MCP (Model Context Protocol) server for macOS that lets MCP-compatible AI assistants send prompts to the ChatGPT desktop app and retrieve responses. It uses Python/FastMCP and automates interaction with the local desktop app (and notes limited language support).
Score Breakdown
⚙ Agent Friendliness
🔒 Security
No network/TLS model is described because this is a local MCP server controlling a desktop app. Authentication/authorization and secret handling are not clearly documented. Use of pyautogui implies GUI automation risks (unintended interactions if the UI state changes).
⚡ Reliability
Best When
You have a macOS machine with the ChatGPT desktop app running, and you want MCP tool access from an MCP-compatible client to drive ChatGPT through that desktop UI.
Avoid When
You need robust multilingual text input, headless/server execution, or strong guarantees around deterministic automation and error recovery.
Use Cases
- • Integrate an MCP client (e.g., Claude Code) with the local ChatGPT desktop app via standard MCP tools
- • Automate sending prompts and retrieving responses without writing a custom UI/automation bridge
- • Enable chat workflow start/new chat plus subsequent message/response retrieval from an MCP agent
Not For
- • Production-grade, server-to-server API access to ChatGPT (it depends on local macOS desktop app automation)
- • Non-English input scenarios (README indicates Korean/other languages may not work reliably, with only English text input supported)
- • Environments where GUI automation is disallowed or unreliable (the package depends on pyautogui)
Interface
Authentication
No explicit authentication mechanism is described for the MCP server; it appears to rely on local execution and operating the user’s installed ChatGPT desktop app.
Pricing
The repository indicates an MIT-licensed open-source MCP server; no pricing details are provided for using the server itself.
Agent Metadata
Known Gotchas
- ⚠ Depends on the ChatGPT macOS desktop app being installed and running
- ⚠ Likely relies on GUI/automation timing; transient UI issues may cause failed tool calls
- ⚠ README notes English text input only; other languages may not work properly
Alternatives
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for chatgpt-mcp.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-30.