Unless the MCP server itself has an LLM call inside of it (rare), the MCP server is pretty deterministic. It’s the AI that invokes it that’s actually indeterministic, but the user is already using that.

This is a very strict definition of MCP. An agent (with LLM call inside) can be an MCP. Event a UI component can be an MCP.

> pretty deterministic

This is an oxymoron.

I meant “pretty” as in, using a search engine is pretty deterministic, any REST API is deterministic.

MCP servers’ tools are literally just function calls. It’s the LLM MCP client that’s not deterministic, not the MCP server.

No it's not.

In the real world, where it is (at least in our current state of overall programming language tooling, and the existence of physics) intractable to prove all eventualities and absence of side-effects of executed code, determinism is indeed a spectrum.

If we want to be specific here, I would say the "pretty deterministic" is equal to "as deterministic as your typical non-LLM REST API call", which still spans a big range of determinism.

Calling it... Vibe clicking

The popularity of slot machines suggests there is a market

AI fills in a form, and you want to adjust the form before clicking submit. How often do you have to adjust AI's answer vs accepting it as is

> button that has indeterministic actions

google.com (1998-present)

    [I'm feeling lucky]