MCP was always a bad idea?
Simon Willison argues MCP still matters for controlled, auditable agent access to external services.
Simon Willison, commenting on a Hacker News thread titled "MCP was always a bad idea?", says MCP still matters for deployments stricter than a fully open terminal agent. He argues it provides control over which external services an agent can reach, authentication that withholds API keys from the agent, a user interface for connecting services, and strong audit logging. Claude Code, Codex, Meta Muse and OpenClaw are named as examples of less-restricted agents that can call APIs directly.
- Unrestricted terminal agents can call APIs without MCP.
- MCP can limit which external services an agent reaches.
- Authentication can keep API keys out of the agent.
- Willison also cites a connect UI and strong audit logs.
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…
This source does not provide full text. Read it at simonwillison.net.