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

I'm wondering if there will be anything that's actually LLM-specific about these API's. Are they useful for ordinary API integration between websites?


Possibly marginally, but the "server" components here are ideally tiny bits of glue that just reformat LLM-generated JSON requests into target-native API requests. Nothing interesting "should" be happening in the context protocol. Examining the source may provide you with information on how to get to the real API for the service, however.




Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

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

Search: