For the Agent to use CLI, don't we have to install CLI in the run-time environment first? Instead for the MCP over streamable HTTP we don't have to install anything and just specify the tool call in the context in't it?

▲

tptacek 12 hours ago | parent [-]

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.

▲

kasey_junk 7 hours ago | parent [-]

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.

	▲	tptacek 7 hours ago \| parent [-]
		Right, this is the part of the problem I get, but a universal meta-API seems like they're overshooting it by a lot.