OpenAI's implementation of MCP in ChatGPT is limited.

· Bits and Bobs 6/9/25
  • OpenAI's[jz] implementation of MCP in ChatGPT is limited.
    • They only allow a subset of allow-listed MCP instances for certain use cases.
    • This will quickly evolve into a kind of app-store distribution system.
      • A closed system.
    • But this is also inevitable given the security and privacy implications of MCP.
    • MCP is extraordinarily dangerous–not only potentially malicious integrations, but also prompt injection within the data in those integrations.
      • This ChatGPT limitation doesn't actually do anything to mitigate prompt injection.
    • When you run a local client with MCP integrations, it's clearly your fault if an MCP integration bites you.
    • But if you're a less-savvy consumer using a feature of a popular chat app and MCP bites you, you're more likely to blame the chat app creator.
    • MCP is not the right way to solve the integration problem for AI.

More on this topic

From other episodes