News for hackers. Stuff that matters.
Re:MCP is the coming of Web 2.0 2.0 by hn_throwaway_99 on Friday May 23, 2025 @08:49PM (#44077956)
> 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.

Re:MCP is the coming of Web 2.0 2.0 by throwaway81523 on Friday May 23, 2025 @10:13PM (#44078247)
Oh great, just what I need for my finance stack, an API with built in AI hallucinations :/
Re:MCP is the coming of Web 2.0 2.0 by nsonha on Saturday May 24, 2025 @12:33AM (#44078798)
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.
Re:MCP is the coming of Web 2.0 2.0 by cma on Saturday May 24, 2025 @11:06PM (#44085225)
> 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.