Max Musing

The Perplexity CTO announced at their developer conference this week that they're moving away from MCP internally. Garry Tan tweeted "MCP sucks honestly." Pieter Levels called it useless. The "MCP is dead, long live the CLI" post hit the top of Hacker News. OpenClaw, the hottest open-source agent project in the world, deliberately chose not to support it.

The argument: MCP tool definitions eat your context window. Auth is clunky. The whole thing is an unnecessary abstraction over APIs that already exist. LLMs are smart enough to call APIs directly, or use CLIs, or write their own integration code. Why add a protocol layer?

For as long as software has existed, the user has been a person. Someone sitting at a desk, poking at a phone, or calling an API. That assumption was so obvious it was never really a design principle, it was just common sense. Every decision about hierarchy, color, button placement, and error messaging was downstream of a single fact: a human being is going to see this.

With agents, that assumption is starting to fail.