Re:From OpenAPI spec to MCP: How we built Xata's MCP server
by ENGNR on Thursday May 29, 2025 @06:22PM
(#44130950)
Agreed, I’ve only implemented one endpoint, but even on that the amount of data coming back was too high, and the json shape ate up context
I think MCP responses will be high level, aggregated, sorted, etc. Also strongly considering YAML over JSON
Re:From OpenAPI spec to MCP: How we built Xata's MCP server
by matt-attack on Friday May 30, 2025 @02:47AM
(#44133589)
Why? Does the a sense of quotes and commas really make a difference in context size?
We have been adding MCP remote server to louie.ai, think a semantic layer over DBs for automating investigations, analytics, and viz over operational systems. MCP is nice so people can now use from Slack, VS Code, CLI, etc, without us building every single integration when they want to use it outside of our AI notebooks. And same starting point of openAPI spec, and even better, fastapi standard web framework for the REST layer.
Using frameworks has been good. However, for chat ergonomics, we find we are defining custom tools, as talking directly to REST APIs is better than nothing, but that doesn't mean it's good. The tool layer isn't that fancy, but getting the ergonomics right matters, at least in our experience. Most of our time has been on security and ergonomics. (And for fun, we had an experiment of vibe coding this while hitting enterprise-level quality goals.)