Are we overengineering AI agents, or am I just lazy?
Are we overengineering AI agents, or am I just lazy?
MCP makes sense when you have multiple agents sharing the same remote service. Real use case, no debate.
But on your laptop? Running a server so your agent can query a database is insane. Just use psql.
We overcomplicated this.
It's faster. It's simpler. Claude already knows how to use these tools.
I kept a few MCP servers where no CLI alternative exists yet. Context7 for example. But that's the exception, not the rule.
Then I just wrote one line in my CLAUDE.md: "Use CLI tools."
psql instead of a Postgres MCP server.
gh instead of a GitHub MCP server.
curl instead of a search MCP server.
agent-browser instead of Playwright MCP server.
Done. No server running. No config. No protocol.
I deleted every MCP server from my Claude Code setup.
I was running MCP servers for everything. Postgres, GitHub, search, browser automation. Background processes running all day waiting for my agent to maybe use them.
I might migrate to Bluesky indefinitely with what is happening on X. Am I the only one ?
New to this, X is good for Tech, Linkedin for showing off. What is this platform good for ?