This rolls up to my original point. I get that if you stipulate the agent can't run code, you need some kind of systems solution to the problem of "let the agent talk to an API". I just don't get why that's a network protocol coupling the agent to the API and attempting to capture the shape of every possible API. That seems... dumb.

Environments where it’s hard to install and configure cli tools and where you want oauth flows.

That is mcp for coding agents is dumb. For gui apps installed at non-cli using non-permissive endpoints it makes a lot of sense.