Live data from Hacker News

OpenAI adds MCP support to Agents SDK

openai.github.io

171–180 of 281 posts

Re: OpenAI adds MCP support to Agents SDK

#171
Can't I do function calling in OpenAPI? I also feel like MCP is reinventing the wheel.

I have been converting OpenAPI documents into function calling schemas and doing tool calling since function calling first came out in 2023, but it's not easy to recreate a backend server to fit MCP.

Also, these days, I'm making a compiler-driven function calling specialized framework, but I'm a little cautious about whether MCP will support it. It enables zero-cost tool calling for TypeScript classes based on the compiler, and it also supports OpenAPI.

However, in the case of MCP, in order to fit this to the compiler-driven philosophy, I need to create a backend framework for MCP development first, or create an add-on library for a famous framework like NestJS. I can do the development, but there's so much more to do compared to OpenAPI tool calling, so it's a bit like that.

Re: OpenAI adds MCP support to Agents SDK

#172

Can't I do function calling in OpenAPI? I also feel like MCP is reinventing the wheel. I have been converting OpenAPI documents into function calling schemas and doing tool calling since function calling first came out in 2023, but it's not easy to recreate a backend server to fit MCP. Also, these days, I'm making a compiler-driven function calling specialized framework, but I'm a little cautious about whether MCP wi…

You’re way over thinking the use cases for MCPs. That tells me you should stick to functions.

Re: OpenAI adds MCP support to Agents SDK

#173
hopefully they integrate it with their customGPT approach! I think they already work fantastically especially since the addition of the @ sign and automatic completion to easily include them in normal conversations. the only thing that was missing was access to the local machine.

Re: OpenAI adds MCP support to Agents SDK

#174
post #167
post #26

I am really struggling with what the value-add is with MCP. It feels like another distraction in the shell game of contemporary AI tech. > MCP is an open protocol that standardizes how applications provide context to LLMs. What is there to standardize? Last I checked, we are using a text-to-text transformer that operates on arbitrary, tokenized strings. Anything that seems fancier than tokens-to-tokens is an illusion…

Well, you should check again, because it hasn't been text to text for a while. There are multimodal models now.

If we want to get pedantic, in context of practical transformer models it has never been text to text. It has always been tokens to tokens. The tokens can represent anything. "multimodal" is a marketing term.

Re: OpenAI adds MCP support to Agents SDK

#175

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": {…

Why is this get_weather location "New York" always an example when people talk about tool calling?

Re: OpenAI adds MCP support to Agents SDK

#176
post #172

Can't I do function calling in OpenAPI? I also feel like MCP is reinventing the wheel. I have been converting OpenAPI documents into function calling schemas and doing tool calling since function calling first came out in 2023, but it's not easy to recreate a backend server to fit MCP. Also, these days, I'm making a compiler-driven function calling specialized framework, but I'm a little cautious about whether MCP wi…

You’re way over thinking the use cases for MCPs. That tells me you should stick to functions.

> That tells me you should stick to functions.

probably we all should ¯\_(ツ)_/¯

Re: OpenAI adds MCP support to Agents SDK

#177
post #14
post #10

I hoped OpenAI would support OpenAPI for connecting to tools. Having created a couple of MCP servers, it feels like a less flexible and worse documented API to me. I can’t really see anything that is made better by MCP over OpenAPI. It’s a little bit less code for a lot less options. Give it some time and it will also get Swagger built in. It’s solving a problem that was already robustly solved. So get we go with ano…

> 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 instantly gained millions of existing sites available to ChatGPT with zero code change.

Re: OpenAI adds MCP support to Agents SDK

#178
post #15
post #11

Earlier quoted context omitted.

so we no longer need langchain and stuff like that, that's a win. But MCP also feels a bit overrated: https://www.lycee.ai/blog/why-mcp-is-mostly-bullshit

I could not find the actual criticism in that article. What's the problem with MCP again? It's the first standard for agents.

http endpoint + function calling can do what MCP do, this extra bad named layer is just jargon festish

Re: OpenAI adds MCP support to Agents SDK

#179
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…

I think this is a good explanation on the client side of MCP. But most developers are not building MCP clients (I think?). Only a few companies like OpenAI, Anthropic, Cursor and Goose are building MCP client.

Most developers are currently building MCP servers that wrap a 3rd party or wrap their own service. And in this case, they are still at deciding on the tools in design-time, not runtime.

Also I want to mention that both Cursor and Claude desktop don't support dynamic toggling on / off tools within a MCP server, which means users can't really pick which tools to expose to AI. It exposes all tools within a MCP server in current implementation.

Re: OpenAI adds MCP support to Agents SDK

#180

Can't I do function calling in OpenAPI? I also feel like MCP is reinventing the wheel. I have been converting OpenAPI documents into function calling schemas and doing tool calling since function calling first came out in 2023, but it's not easy to recreate a backend server to fit MCP. Also, these days, I'm making a compiler-driven function calling specialized framework, but I'm a little cautious about whether MCP wi…

How should an MCP server like git work in your opinion? Should it then be written as a FastAPI server so that you have an openapi spec instead of just a CLI?

https://github.com/modelcontextprotocol/servers/blob/main/sr...

Post reply on HN