MCP was always a bad idea?

王者归来已是老翁AI 前沿📡 Simon Willison's Weblog2026-09-221610 阅读💛 44 收藏

20th September 2026

Comment My comment on MCP was always a bad idea? — Hacker News

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:

  1. Control over exactly which external services it can access
  2. A way to handle authentication that doesn't allow the agent to directly access API keys
  3. A sensible UI to allow users to connect and authenticate further services
  4. 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Thinking MCP is obsolete because full coding agents don't need it misses out on all of the other things we might want to build.

文章评论(12)

山问津2026-09-22

思路清晰,干货满满。

回复
北岛渔夫2026-09-22

整理得太全面了,省了我不少时间。

回复
山问津2026-09-22

看完了,收获满满,期待更多更新。

回复
暮拾贝2026-09-22

作者写得真不错,学到了不少。

回复
山问津2026-09-22

这个比较实用,已转发给同事。

回复
林观澜2026-09-22

赞同,实践出真知。

回复
杨丽华2026-09-22

整理得太全面了,省了我不少时间。

回复
南山客2026-09-22

点赞,必须点赞

回复
杨丽华2026-09-22

收藏了,以后慢慢研究。

回复
墨沐雨2026-09-22

赞同,实践出真知。

回复
青柠微凉2026-09-22

思路清晰,干货满满。

回复
吴超2026-09-22

整理得太全面了,省了我不少时间。

回复