Do MCP's use more tokens than CLI's? (opens in new tab)

There’s a long-held belief out there that MCP’s are bad, and that you should actually use CLI’s instead, if you want to save on token spend. To me that argument has never really made any sense, because you still have to provide the LLM context so it knows what CLI to run, how to run it and how to interpret the result of it. Things that the MCP does for you. How come the CLI takes fewer tokens?