News for hackers. Stuff that matters.

A comment on OpenAI adds MCP support to Agents SDK. Parent comment

Re:OpenAI adds MCP support to Agents SDK by ondrsh on Thursday March 27, 2025 @05:05PM (#43498164)
>In both cases the application code needs to be modified to account for the new functionality, unless you're also using the LLM to handle the logic which will have very unpredictable results.

In the case of MCP, no application code is modified. You first ship the application and then functionality is added. Using plain APIs, it's the other way around. That's the difference.

[ Parent | on HN ]
Re:OpenAI adds MCP support to Agents SDK by Xelynega on Thursday March 27, 2025 @10:20PM (#43500753)
I don't understand this at all.

If my application performs some function dependant on data from an API(e.x. showing tax information, letting a user input tax information, and performing tax calculations and autocomplete), how do I extend that UI easier with MCP than with an HTTP REST API.

Even with MCP I need to update my application code to add UI elements(inputs, outputs) for a user to interact with this new functionality, no?

[ Parent | on HN ]
Re:OpenAI adds MCP support to Agents SDK by ondrsh on Friday March 28, 2025 @05:12AM (#43503162)
No, MCP does not include any concept of UI (yet). Tool results are usually text only, although there is also the abstraction of an Image (which can be displayed as clients as decide to, e.g. inline).
[ Parent | on HN ]
Re:OpenAI adds MCP support to Agents SDK by Xelynega on Sunday March 30, 2025 @06:17PM (#43528248)
So no application code needs to be changed because no application code exists.

Isn't that like saying you don't need to modify application code with an REST API if your "application" is just a list of instructions on how to use wget/bash to accomplish the task?

[ Parent | on HN ]