|
|
|
|
|
by fergie
102 days ago
|
|
> gws doesn't ship a static list of commands. It reads Google's own Discovery Service at runtime and builds its entire command surface dynamically. What is the practical difference between a "discovery service"+API and an MCP server? Surely humans and LLMs are better off using discovery service"+API in all cases? What would be the benefit of MCP? |
|
I have done it many times, using the swagger.json as a "discovery service" and then having the agent utilize that API. A good OpenAPI spec was working perfectly fine for me all the way back when OpenAI introduced GPTs.
If we standardized on a discovery/ endpoint, or something like that, as a more compact description of the API to reduce token usage compared to consuming the somewhat bloated full OpenAPI spec, you would have everything you need right there.
The MCP side quest for AI has been one of the most annoying things in AI in recent years. Complete waste of time.