Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

I have a tool that builds HTTP requests. LLMs can use that just fine, IF they know the API spec they should connect to. And that is the problem. If you are then required to pass the specs of dozens of APIs, you are polluting the context with too much useless info. MCP simplifies that


You also need an MCP schema to understand what the MCP server can actually do, there is no free lunch here.


yes, but in terms of token size its WAY cheaper for the AI to handle that than an OpenAPI spec


Isn't this more a limitation of the OpenAPI spec? Something like GraphQL would probably work much better




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: