Live data from Hacker News

OpenAI adds MCP support to Agents SDK

openai.github.io

91–100 of 281 posts

Re: OpenAI adds MCP support to Agents SDK

#91
post #84

Earlier quoted context omitted.

The `stdio` approach for local services makes complete sense to me. Including using JSONRPC. But for remote HTTP MCP servers there should be a dead simple solution. A couple years ago OpenAI launched plugins as `.well-known/ai-plugin.json`, where it'd contain a link to your API spec, ChatGPT could read it, and voila. So all you needed to implement was this endpoint and ChatGPT could read your whole API. It was pretty…

I agree. What OpenAI did was simple and beautiful. Also, I think there is a fundamental misunderstanding that MCP services are plug and play. They are not. Function names and descriptions are literally prompts so it is almost certain you would need to modify the names or descriptions to add some nuances to how you want these to be called. Since MCP servers are not really meant to be extensible in that sort of way, th…

The good thing to note is that (AFAIK) MCP is intended to be a collaborative and industry-wide effort. Whereas plugins was OpenAI-specific.

So, hopefully, we can contribute and help direct the development! I think this dialogue is helpful and I'm hoping the creators respond via GitHub or otherwise.

Re: OpenAI adds MCP support to Agents SDK

#92
post #73

I'm curious what the revenue plan is for MCP authors. I mean, I can see wanting to add support for existing products (like an code/text editor, image/sound/video editor, etc.) But is there a market for stand-alone paid MCP services? It seems these will mostly be usurped by the models themselves sooner or later. I mean if you create a MCP popular enough to actually make money, the foundation model will soon be able to…

What is the revenue plan for 99% of open source library authors?

Is what you are insinuating that the only licensing model for independent MCP authors is open source? Are you assuming that MCPs are only viable as free (as in beer) projects?

I feel like software license and business revenue models are only very loosely correlated. I guess if you are assuming there is no money at all to be made in MCP then my question wouldn't make sense.

Re: OpenAI adds MCP support to Agents SDK

#94
post #2

They’re all in. They announced they’ll add support for it in the desktop app and the API in the coming months: https://x.com/OpenAIDevs/status/1904957755829481737

I'm surprised this was announced in a random tweet instead of a blog post with a release roadmap or something like that.

because its a lil embarrassing oai didnt come up with it

Re: OpenAI adds MCP support to Agents SDK

#95
Shamelessly promoting in here, I created an architecture that allows an AI agent to have those so called "tools" available locally (under the user control), and works with any kind of LLMs, and with any kind of LLM server (in theory). I've been showing demos about it for months now. Works as a middle-ware, in stream, between the LLM server and the chat client, and works very well. The project is open source, even the repo is outdated, but simply because no one is expressing interest in looking into the code. But here is the repo: https://github.com/khromalabs/Ainara. There's a link to a video in there. Yesterday just recorded a video showcasing DeepSeek V3 as the LLM backend (but could be any from OpenAI as well, or Anthropic, whatever).

Re: OpenAI adds MCP support to Agents SDK

#96
post #70
post #28

> Think of MCP like a USB-C port for AI applications. That analogy may be helpful for mom, but not for me as a software engineer.

To really understand MCP you need to think about application design in a different way. In traditional applications, you know at design-time which functionality will end up in the final product. For example, you might bundle AI tools into the application (e.g. by providing JSON schemas manually). Once you finish coding, you ship the application. Design-time is where most developers are operating in, and it's not wher…

Isn't this just the same paradigm as plugins?

Re: OpenAI adds MCP support to Agents SDK

#97
I'm new to "MCP"... It says here that even IDE plug into this MCP server [1], as in you don't edit files directly anymore but go through a client/server?

It wasn't bad enough that we now run servers locally to constantly compile code and tell us via json we made a typo... Soon we won't even be editing files on a disk, but accessing them through a json-rpc client/server? Am I getting this wrong?

[1] https://modelcontextprotocol.io/introduction

Re: OpenAI adds MCP support to Agents SDK

#98
post #28

> Think of MCP like a USB-C port for AI applications. That analogy may be helpful for mom, but not for me as a software engineer.

I want to know in which way is USB-C applicable here. The complicated plug that's actually 30 different protocol's that's difficult understand what capabiltiies a plug/cable actually has?

Re: OpenAI adds MCP support to Agents SDK

#99
post #73

I'm curious what the revenue plan is for MCP authors. I mean, I can see wanting to add support for existing products (like an code/text editor, image/sound/video editor, etc.) But is there a market for stand-alone paid MCP services? It seems these will mostly be usurped by the models themselves sooner or later. I mean if you create a MCP popular enough to actually make money, the foundation model will soon be able to…

What is the revenue plan for 99% of open source library authors?

The currently-dominant open source paradigm (i.e. motivated and well-meaning developers work themselves to the bone under pressure from tech giants who will never pay them) is clearly not sustainable. Moreover, many are probably not happy with their code being used (without permission) to train machines whose putative intent is to replace those self-same developers. Now the question is, how many will want to do something similar, again?

Re: OpenAI adds MCP support to Agents SDK

#100
post #93

What are people using MCPs for? I search on youtube and see a lot of videos explaining how MCPs work, but none showing practical uses for a programmer (aside from getting the weather via cursor).

I only use one regularly, but I use it a lot. (Supabase)

Example use case: https://news.ycombinator.com/item?id=43466434

Post reply on HN