cd /news/ai-agents/mcp-was-always-a-bad-idea · home topics ai-agents article
[ARTICLE · art-136434] src=simonwillison.net ↗ pub= topic=ai-agents verified=true sentiment=· neutral

MCP was always a bad idea?

A Hacker News commenter pushed back on the argument that MCP (Model Context Protocol) was always a bad idea, saying the critique misses the value MCP provides today. The commenter argued that while full terminal agents such as Claude Code, Codex, Meta Muse, and OpenClaw with unfettered internet access have almost no reason to use MCP and can call APIs directly, MCP makes it easier to operate systems that are less "YOLO" than that. The commenter concluded that treating MCP as obsolete because full coding agents don't need it ignores the other things developers might want to build.

read1 min views1 publishedSep 20, 2026

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Thinking MCP is obsolete because full coding agents don't need it misses out on all of the other things we might want to build.

── more in #ai-agents 4 stories · sorted by recency
── more on @model context protocol 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/mcp-was-always-a-bad…] indexed:0 read:1min 2026-09-20 ·