Re:Turn your best AI prompts into one-click tools in Chrome
by utopiah on Wednesday April 15, 2026 @05:18AM
(#47776618)
What's the difference with complying to OpenAPI specification and providing an endpoint?
Re:Turn your best AI prompts into one-click tools in Chrome
by throwaw12 on Wednesday April 15, 2026 @08:08AM
(#47777965)
OpenAPI is primarily for machine-to-machine which needs determinism and optimized for some cases (e.g. time in unix format with ms accuracy). MCP is optimized for another use case where LLM has many limitations but has good "understanding" of text. instead of sending `{ user: {id: 123123123123, first_name: "XYZYZYZ", "last_name": "SDFSDF", "gender": "..."..... } }` you could return "Mr XYZYZYZ" or "Mrs XYZYZYZ"
llm doesn't need all these and can't parse it anyway without additional tools (e.g. why should it spend tokens even trying to convert unix timestamp to understand the time)
Re:Turn your best AI prompts into one-click tools in Chrome
by hrimfaxi on Wednesday April 15, 2026 @09:50AM
(#47778947)
I thought the whole point of structuring the data was to avoid the LLM from hallucinating/forcing it to conform to a spec?
Re:Turn your best AI prompts into one-click tools in Chrome
by charcircuit on Wednesday April 15, 2026 @08:21AM
(#47778053)
>Remote APIs need hand-crafted endpoints for every possible agent action.
They already need a remote API for every possible user action. MCP is just duplicate work.
WebMCP is currently being incubated in W3C [1], so if it lands as a proper browser standard, this becomes a endpoint every website can expose.
I think browser agents/skills+WebMCP might actually be the killer app for local-first apps [2]. Remote APIs need hand-crafted endpoints for every possible agent action. A local DB exposed via WebMCP gives the agent generic operations (query, insert, upsert, delete) it can freely compose multiple steps of read and writes, at zero latency, offline-capable. The agent operates directly on a data model rather than orchestrating UI interactions, which is what makes complex things actually reliable.
For example the user can ask "Archive all emails I haven't opened in 30 days except from these 3 senders" and the agent then locally runs the nosql query and updates.
- [1] https://webmachinelearning.github.io/webmcp/
- [2] https://rxdb.info/webmcp.html