top | item 44382667

(no title)

xyc | 8 months ago

It's a protocol that doesn't dictate how you are calling the tool. You can use in-memory transport without needing to spin up a server. Your tool can just be a function, but with the flexibility of serving to other clients.

discuss

order

ijk|8 months ago

Are there any examples of that? All the documentation I saw seemed to be about building an MCP server, with very little about connecting an existing inference infrastructure to local functions.