8 comments

[ 2.7 ms ] story [ 29.6 ms ] thread
(comment deleted)
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 :)

> so much slower

unless you're working on 10 features in parallel with smaller models in best-of-4 groups

It is not about optimization but more just having a C++ library.

Then with C++ implementation, you get more portability than Python or other interpreted languages.

If they really cared about performance (which I think is the case since they're using C++ for this) - they should use something else than nholmann-json. It's simple to use, but has one of the most atrocious performance for a C++ JSON library. (The safest choice would probably be RapidJSON)
Hi, I made that port. Performance was not the goal. Just the C++ port mainly.

I also ported the Claude Agent SDK to C++, so fastmcpp is needed for that: https://github.com/0xeb/claude-agent-sdk-cpp

RapidJSON is a good suggestion, maybe I will switch to it at one point.