MCP 是坏主意吗？Simon Willison：受限场景下仍不可替代
MCP was always a bad idea?
Willison 拿 Claude Code 举例：全权限智能体确实不用 MCP，但要管权限、密钥和审计日志就离不开。
Simon Willison 在 Hacker News 上回应"MCP was always a bad idea?"的讨论，认为这种观点忽视了 MCP 当前的实际价值。他指出 Claude Code、Codex 这类能不受限访问互联网的终端智能体，确实可以直接调用 API，用不上 MCP。但对权限收得更紧的场景，MCP 提供了四项关键能力：精确控制智能体可访问的外部服务、不让智能体直接接触 API 密钥的认证方式、供用户连接和授权服务的界面、完整的审计日志。Willison 认为，仅凭全功能编码智能体不需要 MCP 就断定它过时，会漏掉许多其他值得构建的场景。
MCP was always a bad idea?
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: 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 Thinking MCP is obsolete because full coding agents don't need it misses out on all of the other things we might want to build. Tags: hacker-news , model-context-protocol
