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

MCP is dead?

quandri.io

Post reply on HN
Print view View original

381–390 of 444 posts

Re: MCP is dead?

#381

Post by hnlmorg »

tlogan wrote: post #288
hnlmorg wrote: post #182

Earlier quoted context omitted.

That’s only true for the frontier. The moment you start looking at enterprise consumers of AI you’ll see slow monoliths that make decisions by committee and those committees often don’t even understand the tech they’re passing ruling on. And you’ll also often see CISO-offices that are managed by checklists and yet more committees. Asking for MCP access is generally easier than asking for an API for several reasons: 1…

Here is my vision: the future of AI is about truly understanding the real world. The world around us. Not everything in the real world will expose an MCP server so AI can interact with it. Eventually, AI will need to move beyond MCP and interact with the real world the same way humans do: by observing, interpreting, reasoning, and taking action in messy, imperfect environments. MCP tries to organize our messy word to…

The problem isn’t that AI cannot do this already. Because it can. The problem is cost.

There are people complaining that MCP costs too many tokens. Parsing the same UIs that humans do would just be insane.

And to be honest, I don’t think that’s the right goal of AI anyway. Most competent engineers prefer APIs to human interfaces. So why should machine-to-machine use that too?

Re: MCP is dead?

#382

Post by andoando »

PaulHoule wrote: post #262
v3ss0n wrote: post #252

Earlier quoted context omitted.

How in the world MCP is going to be more secure? It introduce a big surface layers for injection attacks and supply chain attacks..

To be devil’s advocate: if you are just running commands with bash or power shell or the like there is no protection. You might have some rules that ban rm -rf ~ but sandboxing in general is not an easy problem.

Youd just whitelist the list of cli calls equivalent to what your mcp offers

Re: MCP is dead?

#383

Post by listless »

mxstbr wrote: post #22

I run the team at OpenAI that's responsible for the ChatGPT App Store, Codex plugins, and all things MCP. The thing that all these "MCP is dead" posts are missing is that whether or not MCP is used as a transport protocol is actually completely irrelevant. The reason MCP isn't dead is because practically ~every company on the planet is building an MCP server. I know this because we interact with all of them. Most of…

Oh man - hearing that we’re building MCP’s where there is no CLI makes me super nervous.

It’s one thing to dupe the functionality of your CLI for better agent integration. It’s another to make it the sole method of interface locking everyone into a spec that we may decide we can do better at some point. Then we gotta pay off all the MCP debt and it will be cheaper to just not.

Re: MCP is dead?

#384

Post by demorro »

willio58 wrote: post #15

> Using existing CLI directly: No context wasted on tool definitions Can someone explain this to me? I've seen claude code try to run a not-well-known package and it basically shot in the dark a command, noticed that failed, then ran the help command for the cli tool to get a list of commands and what they do. How is that different than passing the tools with an MCP? Like how are we saving context?

This is also my point of confusion. People in the comments seem to be saying that MCP is necessary due to discoverability, but I fundamentally fail to understand how a protocol can make interfaces discoverable to an LLM in a way that wouldn't also be achieved by making traditional interfaces more discoverable to a human. These things mimic human behaviour after all.

Surely people aren't saying we haven't solved API discoverability by now and need new tech for it.

Re: MCP is dead?

#385

Post by Someone »

skydhash wrote: post #326
Someone wrote: post #208

Earlier quoted context omitted.

Yes, but you often do not have much control over that. For example try giving a local LLM read access to specific folders in your email account

Easy. What a cron script (that runs as root) that populate a maildir that the agent (restricted user) has access to. The. you restrict network access to the internet, and have it send you its findings by mail (local mail server).

That’s not an example of “Authorisation is a way to do that”, and, I think, not easier than writing a MCP server.

Re: MCP is dead?

#386

Post by kylling »

Dylan16807 wrote: post #372
kylling wrote: post #370

Earlier quoted context omitted.

The parent suggests MCP as a way to secure credentials and enforce guardrails, and sibling comments iterate on this. I might be reading a bit between the lines with my comment, but did not intend to derail the discussion.

But the parent who suggested MCP for security didn't say anything about vibe coding it. The person who talked about vibe coding an MCP was the one saying MCP isn't very useful.

They describe how MCPs are used and implemented in practice.

Re: MCP is dead?

#388

Post by estetlinus »

Dylan16807 wrote: post #372
kylling wrote: post #370

Earlier quoted context omitted.

The parent suggests MCP as a way to secure credentials and enforce guardrails, and sibling comments iterate on this. I might be reading a bit between the lines with my comment, but did not intend to derail the discussion.

But the parent who suggested MCP for security didn't say anything about vibe coding it. The person who talked about vibe coding an MCP was the one saying MCP isn't very useful.

Who in their right mind writes an MCP server by hand? Of course you vibe code them.

Re: MCP is dead?

#389

Post by troupo »

brabel wrote: post #298
troupo wrote: post #261

Earlier quoted context omitted.

This is a great example of the AI-hype-induced reply. > to an LLM that can call tools (since MCP essentially turns an API into a LLM tool). "Tools" is literally an API call > With MCP, the agent sees a bunch of tools it can call, Yes, the agent first calls a specific API that returns the schema for that particular server. It's literally the same. > One more very important factor is authorization, which no one seems t…

If you think tool call and letting the LLM call an API via curl are the same thing, you haven’t a clue how LLMs work and honestly shouldn’t be commenting on the topic at all.

A "tool call" is literally a JSON-RPC call with a predefined schema.

You'd know that if you actually did any of the following:

- read the specification

- implemented an MCP server

- observed communication between client and server

- had any experience beyond what LLMs tell you

Re: MCP is dead?

#390

Post by troupo »

brookst wrote: post #307
troupo wrote: post #253

Earlier quoted context omitted.

> I have some hope that this'll all lead to a revival of semantic web / microformats / etc Why would it? Do you see any agents or models use that? No, instead vibe coders at Anthropic vibe-designed a bespoke protocol that sidesteps and ignores the last 60 years of API development and integrations.

Different levels. Yes, MCP is a hack that could have been carefully built on prior art, and it would have been better for it. Yes, MCP is capable of expressing that prior art, and you can do semantic web concepts even if the wire protocol looks different.

> Different levels.

How are they different?

> Yes, MCP is capable of expressing that prior art, and you can do semantic web concepts even if the wire protocol looks different.

What are you talking about?!

Post reply on HN