I Am the Reason OpenAI Is Killing Unlimited Chats
A developer explains how they used OpenAI's Secure MCP Tunnel to integrate local software development tools directly into ChatGPT. This setup allowed for advanced automation, which the author jokingly suggests may have influenced OpenAI's decision to limit unlimited chat usage.
Why it matters
It illustrates how power users are leveraging new AI integration tools to bypass traditional cloud-based workflows, prompting companies to adjust their service models.
Okay, probably not. But after what I've been doing with ChatGPT, I can understand why they might want to.
OpenAI recently announced changes that will kill unlimited ChatGPT chats and merge it with Codex usage. The unlimited chats I'd been using for development won't work quite the same way.
For the past few months, I've essentially been doing all my software development using unlmited ChatGPT conversations without burning through my Codex limits.
ChatGPT's support for custom MCP servers and OpenAI's Secure MCP Tunnel meant I could expose tools running on my own machines directly to regular ChatGPT conversations.
I built a unified MCP server that runs on my Windows laptop, with a similar setup on my VPS, and integrated a few open-source projects:
Suddenly ordinary ChatGPT converssations could do most of the practical development work I previously used Codex for.
Also covering this story
One other newsroom covered this event. We read that version too.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in