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.
From the original article
My comment on MCP was always a bad idea? — Hacker News. This article entirely misses the value that MCP brings today.
simonwillison.net
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.