MCP is dead. Long live the CLI
March 10, 2026
I’m going to make a bold claim: MCP is already dying. We may not fully realize it yet, but the signs are there. OpenClaw doesn’t support it. Pi doesn’t support it. And for good reason.
I tried to avoid writing this for a long time, but I’m convinced MCP provides no real-world benefit, and that we’d be better off without it. Let me explain.
LLMs are really good at using command-line tools. They’ve been trained on millions of man pages, Stack Overflow answers, and GitHub repos full of shell scripts. When I tell Claude to use
gh pr view 123, it just works.
For several months last year, MCP seemed to be all the rage when it came to AI engineering. But the last few months have definitely seen a cooling of the enthusiasm. Does that just mean they’ve become absorbed into people’s everyday work? or are new practices and patterns emerging that minimize their impact?
This piece echoes things I’ve heard from quite a lot of developers in recent weeks. That they are in effect overkill in many circumstances and there are more lightweight and better solutions available.
