9 times out of 10 my Claude Code is using a bash script before I hook up an MCP to it.
- less tokens required in context (CLAUDE.md vs CLAUDE.md + MCP bloat per request)
- native agent tooling, relying on Bash(my-script params)
- less black box (you & the coding agent can read the scripts)
MCPs are often wrapping restful apis. Turns out agents can use those just fine.
Yeah I wonder just how much MCP is needed when the models seem fine at making REST requests as is, especially if there's an OpenAPI or similar spec available.