← Back to context

Comment by anon84873628

13 hours ago

Ah, so the "I haven't needed it so it must be useless" argument.

There is huge value in having vendors standardize and simplifying their APIs instead of having agent users fix each one individually.

8 comments

anon84873628

Reply
ianbutler  12 hours ago

Possible legit alternative:

Have the agents write code to use APIs? Code based tool calling has literally become a first party way to do tool calling.

We have a bunch of code accessible endpoints and tools with years of authentication handling etc built in.

https://www.anthropic.com/engineering/advanced-tool-use#:~:t...

Feels like this obviates the need for MCP if this is becoming common.

  • anon84873628  12 hours ago

    That solution will not work as well when the interfaces have not been standardized in a way that makes it so easy to import them into a script as a library.

    Coding against every subtly different REST API is as annoying with agents as it is for humans. And it is good to force vendors to define which parts of the interface are actually important and clean them up. Or provide higher level tasks. Why would we ask every client to repeat that work?

    There are also plenty of environments where having agents dynamically write and execute scripts is neither prudent nor efficient. Local MCP servers strike a governance balance in that scenario, and remote ones eliminate the need entirely.

    • simianwords  8 hours ago

      I don’t agree on the first part. What sort of llm can’t understand a swagger spec? Why do you think it can’t understand this but can understand mcp?

      On runtime problems yes maybe we need standardisation.

      2 replies →

ModernMech  6 hours ago

I thought the whole point of AI was that we wouldn't have to do these things anymore. If we're replacing engineering practice with different yet still basically the same engineering practice, then AI doesn't buy us much. If AI lives up to their marketing hype, then we shouldn't need MCP.