News for hackers. Stuff that matters.
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.

There are no comments on this comment yet.