Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI adds MCP support to Agents SDK

openai.github.io

Post reply on HN
Print view View original

201–210 of 281 posts

Re: OpenAI adds MCP support to Agents SDK

#201

Post by tuananh »

ondrsh wrote: post #199
vykthur wrote: post #120

Earlier quoted context omitted.

This a good characterisation of functionality MCP might enable. Thanks. In your opinion, what percentage of apps might benefit from this model where end users bring their own MCP tools to extend the capabilities of your app. What are some good examples of this - e.g., a development tool like Cursor, WindSurf likely apply, but are there others, preferable with end users? How is the user incentivized to upskill towards…

> In your opinion, what percentage of apps might benefit from this model where end users bring their own MCP tools to extend the capabilities of your app. Long term close to 100%. Basically all long-running, user-facing applications. I'm looking through my dock right now and I can imagine using AI tools in almost all of them. The email client could access Slack and Google Drive before drafting a reply, Linear could a…

> local deployment is non-trivial, but this could be solved via something like WASM.

This is why I started working on hyper-mcp which use WASM for plugin development & OCI registry for hosting. You can write Dockerfile for plugin packaging

You develop plugins in any language you want as long as it supports WASM

https://github.com/tuananh/hyper-mcp

Re: OpenAI adds MCP support to Agents SDK

#202

Post by TeMPOraL »

madeofpalk wrote: post #98
talles wrote: 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?

Yes. 99% of that complexity is on the side of implementers - where it should be - and for actual use, approximately everything works well with everything else; specifics matter mostly when you're trying to plug devices that exercise the limits of advanced capabilities. Which sucks, yes, but mostly because implementers/vendors made it this way (would it hurt y'all to label your cables and devices properly, correctly and visibly?!).

Re: OpenAI adds MCP support to Agents SDK

#203

Post by greyman »

otabdeveloper4 wrote: post #183
tcdent wrote: post #4

Big question in my mind was if OpenAI was going to formally endorse this (since it was created by Anthropic) but we have our answer. MCP is now the industry standard for connecting LLMs to external tools.

> MCP is now the industry standard for connecting LLMs to external tools. No it isn't. We're still five or ten years away from real standards. (Anyways it's clear that the future is smaller self-hosted LLMs, so whatever standard eventually emerges will be based on that paradigm.)

1) It isn't a standard yet, but what else apart from filesystem-mcp can be used for prompts like "write me README.md for this repo" (like really produce the file)

2) For me it is not clear the future is smaller self-hosted LLMs. As of today, most useful for me is to use best models, and those are not self-hosted.

Re: OpenAI adds MCP support to Agents SDK

#204

Post by aeonik »

ondrsh wrote: post #70
talles wrote: 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…

You might be able the say the user could "plug in" the new functionality. Or it allows them to "install" a new "application"?

Re: OpenAI adds MCP support to Agents SDK

#205

Post by sethaurus »

slt2021 wrote: post #177
dartos wrote: post #14

Earlier quoted context omitted.

> I can’t really see anything that is made better by MCP over OpenAPI Well it’s transport agnostic, for one. I think a big part of it is defining a stateful connection and codifying the concepts of prompts and tools. Another issue with OpenAPI / swagger is that you still need to create a client per API, but with MCP it’s all uniform.

transport argument is irrelevat when http can be both TCP and UDP, and even if you wanna do one protocol, it can be proxied/tunneled via another protocol transparently via VPN/wireguard/proxy. so transport protocol is moot, especially from latency perspective when most time is spent doing AI inference (seconds) rather than passing packets (milliseconds). I really wish OpenAI just embraced OpenAPI and that would have…

It's transport-agnostic in the sense that it works locally (over stdout), not just remotely. It's not just for web-services. That's why HTTP isn't baked into this.

Re: OpenAI adds MCP support to Agents SDK

#206

Post by ammmir »

keithwhor wrote: post #64

Today MCP added Streamable HTTP [0] which is a huge step forward as it doesn't require an "always-on" connection to remote HTTP servers. However, if you look at the specification it's clear bringing the LSP-style paradigm to remote HTTP servers is adding a bunch of extra complexity. This is a tool call, for example: { "jsonrpc": "2.0", "id": 2, "method": "tools/call", "params": { "name": "get_weather", "arguments": {…

Yeah, I always thought MCP was a bit verbose. It reminds me of the WSDL and SOAP mess of the 2000s. Model tool calls are just RPCs into some other service, so JSON-RPC makes sense. Is there anything else has wide adoption and good client support? XML-RPC? gRPC? Protobufs? I mean, it shouldn't need extra libraries to use. You can handroll a JSON-RPC request/response pretty easily from any programming language.

Regarding the verbosity, yeah, it's interesting how model providers make more money from more tokens used, and you/we end up paying for it somehow. When you're doing lots of tool calls, it adds up!

Re: OpenAI adds MCP support to Agents SDK

#207

Post by soulofmischief »

TeMPOraL wrote: post #191
soulofmischief wrote: post #128

Earlier quoted context omitted.

As it currently stands, MCP is absolutely a security nightmare. Combine this with a general lack of appreciation for security culture amongst developers, and the emerging vibe coding paradigm where non-security-minded people automatically generate and fail to properly audit production-facing code, and it's a disaster waiting to happen. Feels like we've slid back into the 90s in this regard. Great time to be a securit…

> Feels like we've slid back into the 90s in this regard. Thank $deity. 90s and early 2000s were the times software was designed to do useful work and empower users , as opposed to lock them into services and collect telemetry, both of which protected by the best of advancement in security :). I'm only half-joking here. Security is always working against usefulness; MCP is designed to be useful first (like honest to…

A non-exhaustive list of concerns:

- How does a consumer of a remote MCP server trust that it is not saving/modifying their data, or that it is doing something other than what it said it would?

- How does a consumer of a local MCP server trust that it won't wreck their machine or delete data?

- How do servers authorize and authenticate end users? How do we create servers which give different permissions to different users?

These are examples of things which must be done right, and sacrificing user security in order to achieve market dominance is ethically bankrupt. Pedestrians don't know exactly which regulations serve them when a bridge is built, so we don't expect pedestrians to be able to stop corruption and laziness in civil engineering. The same should be true for mass infrastructure; we have a duty as engineers to make the right call.

> MCP, vibe coding, and LLMs in general are briefly giving end-users back some agency, bringing back the whole idea of "bicycle for the mind"

I love what software might look like in 15 years. I don't plan to kill that. I want to protect it, and also protect everyone involved.

Re: OpenAI adds MCP support to Agents SDK

#208

Post by imtringued »

zoogeny wrote: post #83
amerine wrote: post #78

Earlier quoted context omitted.

Not asked contentiously, why does a MCP revenue plan need to exist? It feels like any kind of api-client work any organization or project would build to make users/customers happy and sticky.

Right, that is why I said it makes sense for existing products . I mentioned desktop apps, but it would apply to any existing project. Like JIRA, or HubSpot, Wordpress, or Figma, etc. But there is hype around MCP as if independent devs could do something with it. And some will just for fun, some will for open source cred. But it is my experience that longevity is usually the result of stable revenue. I guess what I p…

The revenue plan for hosted services is that every user with an MCP client will count as a billable user.

Re: OpenAI adds MCP support to Agents SDK

#210

Post by antoinec »

nomilk wrote: 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 have two that I use a lot: - Postgres one connected to my local db - A browser (Playwright) That way I can ask cursor something like: "Find an object with xxx property in the db, open its page in the browser, fix console errors" And it's able to query my db, find relevant object, open the browser, check logs, fix the code based on errors.

Even simpler stuff: - copying pasting a broken local url in cursor, and asking it to fix all console errors. Works really well. - or when you have a complex schema, and need to find some kind of specific record, you can just ask cursor "find me a user that has X transactions, matches Y condition, etc..". I found it much faster than me at finding relevant records

Post reply on HN