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

What if you don't need MCP at all?

mariozechner.at

Post reply on HN
Print view View original

101–110 of 194 posts

Re: What if you don't need MCP at all?

#101

Post by whoknowsidont »

numpad0 wrote: post #98
whoknowsidont wrote: post #92

Earlier quoted context omitted.

>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.

(pedantry)it's something humans are talking about a lot, so up-to-date models do know about it...

Most likely! It's hard to qualify which specific models and version I'm talking about because they're constantly being updated.

But the point is that function & tool calling was already built in. If you take a model from before "MCP" was even referenced on the web it will still _PERFECTLY_ interact with not only other MCP servers and clients but any other API as well.

Re: What if you don't need MCP at all?

#102

Post by alganet »

Instead of tools for humans, and a separate set of tools for machines, we should just make tools for humans+machines.

The agent should look at my README.md, not a custom human-like text that is meant to be read by machines only.

It also should look at `Makefile`, my bash aliases and so on, and just use that.

In fact, many agents are quite good at this (Code Fast 1, Sonnet).

Issue is, we have a LONG debt around those. READMEs often suck, and build files often suck. We just need to make them better.

I see agents as an opportunity for making friendlier repos. The agent is a free usability tester in some sense. If it can't figure out by reading the human docs, then either the agent is not good enough or your docs aren't good enough.

Re: What if you don't need MCP at all?

#103

Post by whoknowsidont »

smallnamespace wrote: post #94
whoknowsidont wrote: post #85

Earlier quoted context omitted.

>This effect is _significantly_ stronger than putting info about available API/cli into CLAUDE.md. No it's not. Honestly this conversation is extremely weird to me because somehow people are gravely misunderstanding what MCP even purports to do, let alone what it actually CAN do in the most ideal situation. It is a protocol and while the merits of that protocol is certainly under active discussion it's irrelevant bec…

Three facts to consider: 1. CLAUDE.md is not part of the system prompt 2. The Claude Code system prompt almost certainly gives directions about how to deal with MCP tools, and may also include the list of tools 3. Instruction adherence is higher when the instructions are placed in the system prompt If you put these three facts together then it’s quite likely that Claude Code usage of a particular tool (in the generic…

>is higher as an MCP server than as a CLI command.

What do you mean by "higher"?

Re: What if you don't need MCP at all?

#104

Post by tuananh »

rsanheim wrote: post #91
nestorD wrote: post #39

So far I have seen two genuinely good arguments for the use of MCPs: * They can encapsulate (API) credentials, keeping those out of reach of the model, * Contrary to APIs, they can change their interface whenever they want and with little consequences.

But …you have to give the MCP the creds somehow. Maybe it’s via a file on disk (bad), maybe via an env var (less bad). Maybe you do it via your password CLI that you biometricly auth to, which involves a timeout of some sort for security, but that often means you can’t leave an agent unattended. In any case, how is any of this better than a CLI? CLIs have the same access models and tradeoffs, and a persistent agent w…

mcp is easy to self-host. model? a little less so.

Re: What if you don't need MCP at all?

#105

Post by mountainriver »

almosthere wrote: post #28
elliotto wrote: post #25

[flagged]

AI is in it's "pre react" state if you were to compare this with FE software development of 2008-2015

We won’t have a rails or react for AI, that’s insane. As it gets smarter you’ll just talk to it lol.

All of this is just software engineers grasping to stay relevant

Re: What if you don't need MCP at all?

#106

Post by sumeno »

whoknowsidont wrote: post #99
choilive wrote: post #95

Earlier quoted context omitted.

That is an easily falsifiable statement. If I ask ChatGPT or Claude what MCP is Model Context Protocol comes up, and furthermore it can clearly explain what MCP does. That seems unlikely to be a coincidental hallucination.

Training data =/= web search Both ChatGPT and Claude will perform web searches when you ask them a question, which the fact that you got this confused is ironically topical. But you're still misunderstanding the principle point because at some point these models will undoubtedly have access to that data and be trained on it. But they didn't need to be, because LLM function & tool calling is already trained on these m…

Claude gives me a lengthy explanation of MCP with web search disabled

Re: What if you don't need MCP at all?

#107

Post by didibus »

> Each tool is a simple Node.js script that uses Puppeteer Core. By reading that README, the agent knows the available tools, when to use them, and how to use them via Bash.

> When I start a session where the agent needs to interact with a browser, I just tell it to read that file in full and that's all it needs to be effective. Let's walk through their implementations to see how little code this actually is.

Cool, now you want to package that so others can use it? What next?

Put it behind an MCP is an easy approach. Then I can just install that MCP and by choosing it I have all the capabilities mentioned here.

Or in this particular case, a Claude Skill could likely do as well.

But I mean, that's MCP. I don't even really understand the people discussing that MCP is bad or whatever, it's a plug and play protocol so I can package tools for others to use in their preferred agent client.

CLI access also has the issue that if you want to integrate it in an application, well how do you bundle bash in a secure way so your agent can use it? And would you allow users custom tool call, now they can run arbitrary bash commands?

Re: What if you don't need MCP at all?

#108

Post by didibus »

whoknowsidont wrote: post #15

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…

> MCP was a really shitty attempt at building a plugin framework

Can you go more in depth? The protocol is relatively simple, what about it you feel is "shitty" as a plugin framework?

Re: What if you don't need MCP at all?

#109

Post by whoknowsidont »

sumeno wrote: post #106
whoknowsidont wrote: post #99

Earlier quoted context omitted.

Training data =/= web search Both ChatGPT and Claude will perform web searches when you ask them a question, which the fact that you got this confused is ironically topical. But you're still misunderstanding the principle point because at some point these models will undoubtedly have access to that data and be trained on it. But they didn't need to be, because LLM function & tool calling is already trained on these m…

Claude gives me a lengthy explanation of MCP with web search disabled

Great! It's still irrelevant.

Re: What if you don't need MCP at all?

#110

Post by cookiengineer »

whoknowsidont wrote: post #92
paulddraper wrote: post #87

Earlier quoted context omitted.

> 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.)

>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.

> That is a factual statement,

I think most people, even most devs, don't actually know how crappy an MCP client is built, and that it's essentially an MITM approach and that the client sends the LLM on the other end a crappy pretext of what tools are mounted and how to call their methods in a JSON, and then tries to intelligently guess what response was a tool call.

And that intelligent guess is where it gets interesting for pentesting, because you cannot guess anything failsafe.

Post reply on HN