MCP 一直都是个坏主意？

MCP was always a bad idea?

AI 导读

MCP 并未因完整终端智能体用不上就失去今天的价值，更克制的场景里它让服务访问控制、认证、连接界面和审计都更容易提供。如果运行的是 Claude Code、Codex、Meta Muse、OpenClaw 等拥有不受限制互联网访问的完整终端智能体，几乎没有理由使用 MCP，直接让它调用 API 即可。

正文

20th September 2026

This article entirely misses the value that MCP brings today.

Sure, there's almost no reason to use MCPs if you are running a full-blown terminal agent (Claude Code, Codex, Meta Muse, OpenClaw etc) with unfettered internet access - just let it call APIs directly.

If you want to operate something that's less YOLO than that, you'll find yourself wanting:

Control over exactly which external services it can access
A way to handle authentication that doesn't allow the agent to directly access API keys
A sensible UI to allow users to connect and authenticate further services
Strong audit logging for what's going on

MCP makes all of that so much easier to provide.

Thinking MCP is obsolete because full coding agents don't need it misses out on all of the other things we might want to build.

来源：Simon Willison · simonwillison.net