Unecessary complication. LLM Can call tools without MCP 100% fine. You don't need a Stateful SSE JSORPC Meshedup server running APIs rebraneded as tools at somewhere on the cloud .

I think there's going to be a lot of places where you want the middleare that's only exposing a sub-set of apis. and the Ideas that you copy some URL, put it in your LLM Client, and then it magically gets all the tools/endpoints available to you, and you start interacting with it, simplifies the process greatly for a lot of users. No swagger, no http post, body vs params, etc....just play with with your prompt sentance until you get it to do what you want.

(edit: sorry, I responded to wrong thread.)

Yeah that but - Why SSE? - Why JsonRPC - Why Statefulness

REST based Tool Call Server would work 100% fine. Now auth have to be redone for those specifically.

And for users of MCP Tools - they are sending a lot of their information to whatever service they are running - that they have never control of

For developer it is not necessary and security nightmare if you use someone's MCP service or run your own.

For users , it is a privacy nightmare .

> LLM Can call tools without MCP 100% fine.

but can the LLM host UI ask me for permission (in an outside-of-LLM domain) if the LLM wants to call API foo.bar ?

Thats all part of how you code the LLMHost Backend and Frontend. I build several MCP and MCP-Less tool calling agents using autogen and they can ask the user permission. That is nothing to do with MCP at all.

Look into AutoGen by microsoft or if you want more basic , learn how tool calling in LLMs work.

MCP is the React for tool calling agents. There is also Angular (langchain?) and vanilla, rolling your own. React won.

> Thats all part of how you code

I mean I certainly don't want to code my own LLM UI

Sounds like NPM:)