Comment by noogai03
7 hours ago
I find the idea of highly optimised MCP kind of funny. The protocol is so far from finished - the update for stateless MCP (which is our only hope at properly scaling it) isn't even released yet in the core protocol.
And even then - the LLMs are going to be so much slower than the MCP server, I've never quite understood the point of trying to optimise it. Even FastMCP is pretty good because everything is async.
But even given all that - this is very impressive :)
The agents call the MCPs, which could reside on resource constrained environments or devices. Other situations like MCPs that run on your laptop are better off as self contained binaries (my personal and probably unpopular opinion ;) ).
So MCP optimization may be something that’s targeted to those areas.