←back to thread

What if you don't need MCP at all?

(mariozechner.at)
237 points jdkee | 3 comments | 16 Nov 25 18:58 UTC | HN request time: 0.477s | source
Show context
whoknowsidont ◴[16 Nov 25 21:37 UTC] No.45948637[source]▶
MCP was a really shitty attempt at building a plugin framework that was vague enough to lure people into and then allow other companies to build plugin platforms to take care of the MCP non-sense.

"What is MCP, what does it bring to the table? Who knows. What does it do? The LLM stuff! Pay us $10 a month thanks!"

LLM's have function / tool calling built into them. No major models have any direct knowledge of MCP.

Not only do you not need MCP, but you should actively avoid using it.

Stick with tried and proven API standards that are actually observable and secure and let your models/agents directly interact with those API endpoints.

replies(8): >>45948748 #>>45949815 #>>45950303 #>>45950716 #>>45950817 #>>45951274 #>>45951510 #>>45951951 #
paulddraper ◴[17 Nov 25 02:15 UTC] No.45950303[source]▶
> No major models have any direct knowledge of MCP.

Claude and ChatGPT both support MCP, as does the OpenAI Agents SDK.

(If you mean the LLM itself, it is "known" at least as much as any other protocol. For whatever that means.)

replies(1): >>45950488 #
whoknowsidont ◴[17 Nov 25 02:57 UTC] No.45950488[source]▶
>it is "known" at least as much as any other protocol.

No. It is not. Please understand what the LLM's are doing. Claude nor ChatGPT nor any major model knows what MCP is.

They know how to function & tool call. They have zero trained data on MCP.

That is a factual statement, not an opinion.

replies(6): >>45950540 #>>45950541 #>>45950569 #>>45950763 #>>45950803 #>>45951338 #
paulddraper ◴[17 Nov 25 04:12 UTC] No.45950803[source]▶
> They have zero trained data on MCP.

They have significant data trained on MCP.

> They know how to function & tool call.

Right. You can either use MCP to transmit those tool calls, or you can create some other interface.

replies(1): >>45950854 #
whoknowsidont ◴[17 Nov 25 04:30 UTC] No.45950854[source]▶
>They have significant data trained on MCP.

No they don't lol.

replies(1): >>45954410 #
1. paulddraper ◴[17 Nov 25 15:28 UTC] No.45954410[source]▶
Wild claim.

MCP has been popular for well over a year.

To filter it out of the training data would be laughable.

replies(2): >>45955218 #>>45958411 #
2. whoknowsidont ◴[17 Nov 25 16:36 UTC] No.45955218[source]▶
Please give this a read before engaging further: https://huggingface.co/docs/hugs/en/guides/function-calling

You're just utilizing your ignorance to yap at this point.

3. cstrahan ◴[17 Nov 25 21:16 UTC] No.45958411[source]▶
What whoknowsidont is trying to say (IIUC): the models aren't trained on particular MCP use. Yes, the models "know" what MCP is. But the point is that they don't necessarily have MCP details baked in -- if they did, there would be no point in having MCP support serving prompts / tool descriptions.

Well, arguably descriptions could be beneficial for interfaces that let you interactively test MCP tools, but that's certainly not the main reason. The main reason is that the models need to be informed about what the MCP server provides, and how to use it (where "how to use it" in this context means "what is the schema and intent behind the specific inputs/outputs" -- tool calls are baked into the training, and the OpenAI docs give a good example: https://platform.openai.com/docs/guides/function-calling).