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

331–340 of 444 posts

Re: MCP is dead?

#331

Post by solarkraft »

It's such a dumb discussion.

MCP is an API with some description. It adds tools to your agent, along with some context.

The (common) complaint is that the principle of progressive disclosure isn't working because all tools, with all their descriptions, are loaded into context right at the start. This is a somewhat reasonable complaint, as the structure makes it hard for the harness to progressively disclose the tools.

This is a fundamental issue with anything that just adds a bunch of tools, whether it be via MCP or HTTP (still sad that MCP won over OpenAI's HTTP based approach).

How might it be solved? Well, we could work with sets of tools. That's pretty much what the CLI approach does: Wait until you need it, then invoke the help command to discover what to do exactly. The caveat of the CLI being that it's a nightmare to secure.

At the end of the day, every capability eats some amount of context because the LLM needs to know when to invoke it.

Re: MCP is dead?

#332

Post by losvedir »

holoduke wrote: post #200
tlogan wrote: post #112

Earlier quoted context omitted.

I would bet that MCP is going to die. The main reason is that it adds another layer (and human) that can, and probably will, get out of sync with the real-world implementation, whether that implementation is an API, web, or a CLI. AI should not be using a protocol or set of instructions that is different from what humans have access to (know and use). Sure, companies want to expose MCP servers because it is the cool…

Funny thing is that Claude knows the api of Atlassian better than the mcp they provide. Mcp is limited it doesn't have all api calls described.

I haven't found this to be the case. I tried to make `acli` work, with CLAUDE.md fine saving the things Claude learns about how to use the API (eg which custom variables to include and so on), but in the end found the MCP to work better. I think I had trouble getting the CLI to update a certain custom field, which the MCP was able to do. Not to mention, I don't think `acli` even works with Confluence?

Re: MCP is dead?

#333

Post by jaynate »

btbuildem wrote: post #301
jaynate wrote: post #91

Feels like we’re continuing to trend toward deterministic workflows which may actually be okay in 90% of cases. Reality is there’s a lot of unnecessary token burn happening right now. Simple market dynamics will solve that, i.e., when token cost subsidies begin to fade away and we face the true cost of agent applications.

Bingo. All this agentic hype is just people discovering POCs. Yes you can hodgepodge semi-reliable solutions where you don't really know what you're trying to build so you wrap it in a layer than can sometimes approximate logic and decision making, so that you don't have to use logic or make decisions. Amazing. Sooner or later you have to build the real thing, and the cost and slowness of token-based computation beco…

Yes, and the free-for-all building of nonsense (and insecure) apps by non engineers is probably going to slow down as well.

Re: MCP is dead?

#334

Post by mikojan »

dropofwill wrote: post #320
mrgaro wrote: post #294

Earlier quoted context omitted.

Another examole which is trivial with MCP but hard with cli binaries: blocking certain commands, such as write operations from the agent. With MCP your client can easily have a blocklist for commands, but with cli you would need to code custom logic for each cli separately.

Just use scopes in the API key the agent uses? If you’re exposing something publicly that should be a requirement anyways. That’s how I use gh, aws, etc. No need to modify any of the code in the cli, they’re just wrappers.

I want the harness to use read freely but require confirmation for write.

Re: MCP is dead?

#335

Post by fireant »

Besides points already mentioned,

- remote mcps are server driven, meaning the producer can introduce new functionality without requiring all clients to update their skills and clis

- remote mcps are safe as they don't require literal code execution privileges on your system. Many times skills even bundle scripts with `npx`/`uvx` which is basically just `curl npm.com | bash` level of unsafe

Re: MCP is dead?

#336

Post by notatoad »

PhilipRoman wrote: post #189
notatoad wrote: post #86

Earlier quoted context omitted.

right, but if you have 300 employees using ai and you want to share a skill with all of them, and you want to be able to push an update to the skill, mcp provides you with a standard way to do that. i dont understand why people are so invested in making this a winner-take-all battle. skills are ligthweight and ad-hoc, MCP is managed and centralized. there's a place for both of those things, even if your personal work…

Don't most companies have a Git repo for skills that you can pull?

for developers working in claude code, sure. but there's ai users who don't use claude code. chatGPT business and enterprise tiers integrate with MCP servers controlled by your organization admin.

Re: MCP is dead?

#337

Post by jmkni »

zwischenzug wrote: post #204
js4ever wrote: post #148

Earlier quoted context omitted.

Totally agree, MCP is the WAP equivalent of mobile internet access.

I'm old enough to get this reference! Spent years writing WAP... it was really great at the time.

It blew my mind as a kid

I was maybe 10/11 when the Nokia 3330 came out, and being able to use the internet while not in front of a computer just felt like magic

Re: MCP is dead?

#339

Post by notnmeyer »

nsonha wrote: post #308
clarkdale wrote: post #293

Earlier quoted context omitted.

I can't pipe an MCP's output to jq, and I can't ask an AI to write a python script to call an MCP.

sorry both of the things you said are false, why are they stated so confidently?

because being confidently incorrect is a thing?
Post reply on HN