News for hackers. Stuff that matters.
Re:From OpenAPI spec to MCP: How we built Xata's MCP server by alooPotato on Tuesday May 27, 2025 @01:31PM (#44108978)
i really dont get why we cant just feed the openapi spec to the LLM instead of having this intermediate MCP representation. Don't really buy the whole 'the api docs will overwhelm an LLM" - that hasn't been my experience.
Re:From OpenAPI spec to MCP: How we built Xata's MCP server by wild_egg on Tuesday May 27, 2025 @01:47PM (#44109138)
I haven't looked at MCP payloads properly to compare but often the raw OpenAPI spec is overly verbose and eats context space pretty quick.

Really trivial to have the LLM first filter it down to the sections it cares about and then condense those sections though.

Wrap that process in a small tool and give that to the LLM along with a `fetch` tool that handles credentials based on URLs and agent capabilities explode pretty rapidly.

Re:From OpenAPI spec to MCP: How we built Xata's MCP server by crystal_revenge on Tuesday May 27, 2025 @02:38PM (#44109556)
I see this question frequently related to MCP, but I'm guessing these questions come from people who haven't built a lot of products using LLMs?

Even if you're LLM could learn the openai spec, you still have to figure out how to concretely receive a response back. This is necessary for virtually any application build using an LLM and requires support for far, far more use cases than just calling an API.

Consider the following use case: - You need to include some relevant contextual data from a local RAG system. - There are local functions that you want the model to be able to call - The API example you describe - You need to access data from a database

In all of these cases, if you have experience working with LLMs, you've implemented some ad hoc template solution to pass the context into the model. You might have writing something like "Here is the info relevant to this task {{info}}" or "These are the tools you can use {{tools}}", but in each case you've had to craft a prompting solution specific to one problem.

MCP solves this by making a generic interface to sending a wide range of information to the model to make use of. While the hype can be a bit much, it's a pretty good (minus the lack of foresight around security) and obvious solution to this current problem in AI Engineering.

Re:From OpenAPI spec to MCP: How we built Xata's MCP server by wild_egg on Tuesday May 27, 2025 @02:55PM (#44109697)
> you still have to figure out how to concretely receive a response back

Isn't that handled by whatever Tool API you're using? There's usually a `function_call_output` or `tool_result` message type. I haven't had a need for a separate protocol just to send responses.

Re:From OpenAPI spec to MCP: How we built Xata's MCP server by otabdeveloper4 on Tuesday May 27, 2025 @02:45PM (#44109624)
Just ask the model to respond with JSON. Give it a template example response.

You don't need a spec.

For sending prompts to the LLM you will absolutely need to hand-craft custom prompts anyways, as each model responds slightly different.

Re:From OpenAPI spec to MCP: How we built Xata's MCP server by truemotive on Tuesday May 27, 2025 @05:37PM (#44110860)
If you're working from OpenAPI, ideally you want to be able to process any, potentially full of shit formatting spec file. I find that half the integrations I run into have some old weird version of Swagger, and the rest work like hell to stay up to date with the 3.x spec track.

I agree, I wish, it will be a solved problem eventually. Just feeding a complex data model like that to the paper shredder that is the LLM, for making decisions about whether DELETE or POST is used is just asking for trouble.