Hacker News Reader

Comment by Karrot_Kream | Hacker News Reader

Sure but there are established alternatives for that also. The internet supports looking up DNS records (A, MX, SRV, TXT, etc), the web offers /.well-known as a place to store things like API endpoint specs, etc. The main difference with MCP is that the discoverability comes with the stream-oriented communication semantics.

View on HN

Well, you’re basically saying that different domains have different solutions to this problem. There isn’t a universally accepted way to do client discovery, and what exists are very specific to those domains.

I don't think it's accurate to describe .well-known as "very specific to [a domain]"

It’s at least restricted to http servers. Certainly more once you include domain specific conventions

> There isn’t a universally accepted way to do client discovery, and what exists are very specific to those domains.

I commented elsewhere on this recently, https://news.ycombinator.com/item?id=44063680, but a huge value of LLMs is you don't need a "universally accepted way to do client discovery" - if you have an exposed API that already supports one of the bajillion standards that expose schema information (e.g. Swagger/OpenAPI, GraphQL, SOAP, etc.), then any decent LLM should just be able to figure out how to use it.

This idea that we need "one more universal interop standard to rule them all" seems to me like a very pre-LLM way of thinking.

Oh great, just what I need for my finance stack, an API with built in AI hallucinations :/

the thing with building interconnected software is that we should resist the urge to just let the AI perform magic and somehow reliably mix and match all these overlapping things. We should have ONE clearly defined contract. There is no evidence that this principle can be challenged even at the current state of LLM.

> if you have an exposed API that already supports one of the bajillion standards that expose schema information

I don't know jf they are doing it well with MCP, but if a solution has one extra round trip in the model for a dependent read it has to reprocess the entire context or store it into a cache hierarchy possibly burning several hundred gigs of ssd write durability if it isn't a short enough time to cache in system RAM.

> There isn’t a universally accepted way to do client discovery

Someone should really create a protocol to transfer hyper text where clients could discover resources through embedded links in documents

Reply on news.ycombinator.com