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

MCP doesn't need tools, it needs code

lucumr.pocoo.org

Post reply on HN
Print view View original

51–60 of 146 posts

Re: MCP doesn't need tools, it needs code

#51

Post by scosman »

I made a MCP server that tries to address some of these (undocumented, security, discoverability, platform specific). You write a yaml describing your tools (lint/format/test/build), and it exposes them to agents MCP. Kinda like package.json scripts but for agents. Speeds things up too, fewer incorrect commands, no human approval needed, and parallel execution.

https://github.com/scosman/hooks_mcp

The interactive lldb session here is super cool for deeper debugging. For security, containers seem like the solution - sketch.dev is my fav take on containerizing agents at the moment.

Re: MCP doesn't need tools, it needs code

#52

Post by nativeit »

nsonha wrote: post #32
jumploops wrote: post #20

The promise of MCP is that it “connects your models with the world”[0]. In my experience, it’s actually quite the opposite. By giving an LLM a set of tools, 30 in the Playwright case from the article, you’re essentially restricting what it can do. In this sense, MCP is more of a guardrail/sandbox for an LLM, rather than a superpower (you must choose one of these Stripe commands!). This is good for some cases, where y…

It's not guardrail, it's guidance. You don't guide a child or an intern with: "here is everything under the sun, just do things", you give them a framework, programming language, or general direction to operate within.

Interns and children didn’t cost $500B.

Re: MCP doesn't need tools, it needs code

#53

Post by nsonha »

nativeit wrote: post #52
nsonha wrote: post #32

Earlier quoted context omitted.

It's not guardrail, it's guidance. You don't guide a child or an intern with: "here is everything under the sun, just do things", you give them a framework, programming language, or general direction to operate within.

Interns and children didn’t cost $500B.

Some of them quip on HN, quite impressive.

Re: MCP doesn't need tools, it needs code

#54

Post by lsaferite »

tronreference wrote: post #17
reactordev wrote: post #4

Earlier quoted context omitted.

MCP is Model Context Protocol, welcome to the land of the living. Make sure you turn the lights off to the cave. :) It’s pretty well known by now what MCP stands for, unless you were referring to something else…

Master Control Program: https://www.youtube.com/watch?v=atmQjQjoZCQ

I refuse to believe they didn't name the spec with that in mind.

Also... that's some dedication. A user dedicated to a single comment.

Re: MCP doesn't need tools, it needs code

#55

Post by jumploops »

PhilippGille wrote: post #38
jumploops wrote: post #20

The promise of MCP is that it “connects your models with the world”[0]. In my experience, it’s actually quite the opposite. By giving an LLM a set of tools, 30 in the Playwright case from the article, you’re essentially restricting what it can do. In this sense, MCP is more of a guardrail/sandbox for an LLM, rather than a superpower (you must choose one of these Stripe commands!). This is good for some cases, where y…

Given the security issues that come with MCP [1], I think it's a bad idea to call MCP a "guardrail/sandbox". Also, there are MCP servers that allow running any command in your terminal, including apt install / brew install etc. [1] https://simonwillison.net/2025/Jun/16/the-lethal-trifecta/

Yeah admittedly poor choice of words, given the security context surrounding MCP at large.

Maybe “fettered” is better?

Compared to giving the LLM full access to your machine (direct shell, Python executable as in the article), I still think it’s right way to frame MCP.

We should view the whole LLM computer interface as untrusted, until proven otherwise.

MCP can theoretically provide gated access to external resources, unfortunately many of them provide direct access to your machine and/or the internet, making them ripe as an attack vector.

Re: MCP doesn't need tools, it needs code

#56

Post by bityard »

losvedir wrote: post #25
yxhuvud wrote: post #2

First rule of writing about something that can be abbreviated: First have some explanation so people have an idea of what you are talking about. Either type out what the abbreviation stands for, have an explanation or at least a link to some other page that explain what is going on. EDIT: This has since been fixed in link, so it is outdated.

If you don't know what "MCP" stands for, then this article isn't for you. It's okay to load it, realize you're not the target audience, and move on. Or, spend some of your own time looking it up. This is like complaining that HTTP or API isn't explained.

Textbook example of gatekeeping if I ever saw it.

Re: MCP doesn't need tools, it needs code

#59

Post by Bjartr »

nativeit wrote: post #52
nsonha wrote: post #32

Earlier quoted context omitted.

It's not guardrail, it's guidance. You don't guide a child or an intern with: "here is everything under the sun, just do things", you give them a framework, programming language, or general direction to operate within.

Interns and children didn’t cost $500B.

Collectively they kind of do and then some. That cost for AI is in aggregate, so really it should be compared to the cost of living + raising children to be educated and become interns.

At some point the hope for both is that they result in a net benefit society.

Re: MCP doesn't need tools, it needs code

#60

Post by senko »

nativeit wrote: post #52
nsonha wrote: post #32

Earlier quoted context omitted.

It's not guardrail, it's guidance. You don't guide a child or an intern with: "here is everything under the sun, just do things", you give them a framework, programming language, or general direction to operate within.

Interns and children didn’t cost $500B.

How is that relevant?
Post reply on HN