I agree. In any large backend software running on a server, it's the LLM invocation which would be a call out to an external system, and with proper validation around the results. At which point, calling an "MCP Server" is also just your backend software invoking one more library/service based on inspecting some part of the response from the LLM.
This doesn't take away from the utility of MCP when it comes Claude Desktop and the likes!
Hooks into the agent's execution lifecycle seem more reliable for deterministic behavior and supervision.