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

When does MCP make sense vs CLI?

ejholmes.github.io

Post reply on HN
Print view View original

271–280 of 301 posts

Re: When does MCP make sense vs CLI?

#271

Post by notepad0x90 »

woctordho wrote: post #247
notepad0x90 wrote: post #227

Earlier quoted context omitted.

Because that is a consistent and reliable way of doing it? what happens when I have to use something that can't be done via cli, or if I have lots of small use cases (like I sometimes do with MCP servers - lots of tiny functions), do I create a separate readme for each of them and manage the mess? what exactly is the issue with MCP? is it too well organized? I mean technically I could be using cli tools to browse HN…

There are certainly things can't be done via CLI, or more suitable for a persistent daemon with various RPC rather than a CLI. But most things are simpler than that, and MCP is overcomplicating it. MCP does not make things more organized. Everything is a file, and the filesystem is a mature infrastructure that we can trust. I don't see how MCP can be more organized than it. curl is a great example of what CLI can do.…

Maybe I don't understand how other people are using MCP, if it is for code generation agents, that I can't speak of. but for your own agent code, for me at least an MCP server is much easier to use than running commands directly.

> Is there really a better way than curl for AI to browse HN?

Yes, curl can't render the DOM and HN requires captcha when registering. WebMCP is a better way!

Re: When does MCP make sense vs CLI?

#272

Post by sunir »

baruch wrote: post #221
sunir wrote: post #192

The only place MCP made sense for me, so I thought, was to give my Claude Web agents access to the same cli tools my Claude Code agents had. In this context, agents don't have shells. However, then I discovered MCP servers on Claude Web are forced onto my laptop for Claude Code, which is very confusing. I don't know if there is a way to stop that, but it has messed up my Claude Code agents. Is this experience common,…

There is a global setting you can do to disable using the Claude.ai MCPs from being used on your Claude code.

Thank you so much.

Re: When does MCP make sense vs CLI?

#273

Post by mdemare »

Myrmornis wrote: post #269

Most of what the article says is true regarding coding agents, but articles like this are making a big mistake: they're completely forgetting that agentic applications aren't all claude code. We're entering an era where many organisations will have agentic loops running in their own backends. There's a spectrum of constraint that can be applied to these apps -- at one end claude code running unsandboxed on your lapto…

Sure, but it's pretty trivial to generate a CLI application that talks to that API.

That's how I let agents access my database too. Letting them access psql is a recipe for disaster, but a CLI executable that contains the credentials, and provides access to a number of predefined queries and commands? That's pretty convenient.

Re: When does MCP make sense vs CLI?

#274

Post by xmcqdpt2 »

vrosas wrote: post #256
D-Machine wrote: post #238

Earlier quoted context omitted.

Because "him" is objectively wrong, under almost any interpretation of any words involved. You can cause Claude, or any text-based LLM, to emit language that matches almost any personality / gender / character in the training set. At best you might be able to say "the default outputs have a masculine tone / vibe", but this still doesn't justify, by modern discourse, the "him".

You took the time to write this entire paragraph and didn’t realize it’s just because Claude is a masculine name?

I thought they picked it specifically because it is gender neutral, but now I double checked and apparently it's only gender neutral in French,

https://en.wikipedia.org/wiki/Claude_(given_name)

Re: When does MCP make sense vs CLI?

#275

Post by sigmoid10 »

phpnode wrote: post #57
sigmoid10 wrote: post #12

Earlier quoted context omitted.

>we can expect it to get much better than it is today Which is not a high bar to clear. It literally only got where it is now because execs and product people love themselves another standard, because if they get their products to support it they can write that on some excel sheet as shipped feature and pin it on their chest. Even if the standard sucks on a technical level and the spec changes all the time.

This is excessively cynical, it's a useful tool despite its shortcomings.

You could strip away 90% of the spec and it would be even more useful. In fact standardizing the tool definitions and prompt formats would probably have done more if you're serious about supporting a certain set of tools between various LLM providers.

Re: When does MCP make sense vs CLI?

#276

Post by jFriedensreich »

This take is so incredibly short sighted. Sure mcp is not perfect and needs better tooling and a bit updated standards, but clis are >maybetarget sandbox individual MCP tools MCP Gateway Agent Server

we will find a way to make mcp more composable for the cases subagents are not efficient / reproducible enough

Re: When does MCP make sense vs CLI?

#278

Post by mentalgear »

> CLIs have had decades of design iteration. They’re composable, debuggable, and they piggyback on auth systems that already exist. MCP tried to build a better abstraction. Turns out we already had a pretty good one.

I found MCP always cumbersome, and who would have thought that the cli, around since the dawn of digital computers and thoroughly saturated in the training data of every LLM, would be the better tool.

Re: When does MCP make sense vs CLI?

#279

Post by stldev »

baruch wrote: post #237
stldev wrote: post #131

I've found MCP is great for stacking claude code instances- https://github.com/cduerr/stewardmcp has legit been a useful tool for me, and more reliable than handing a single instance 100k lines of code over a dozen repos.

Isn't that handled pretty well these days with sub agents? They can research the code without polluting the context.

Somewhat. The stewards (sub-Claudes) won't share their parents context window and have the ability to talk to one another. That said I'm sure there's a lot out there that solves for this.

Re: When does MCP make sense vs CLI?

#280

Post by jeremyjh »

ashdksnndck wrote: post #56
jeremyjh wrote: post #54

Earlier quoted context omitted.

No, it really matters because of the impact it has on context tokens. Reading on GH issue with MCP burns 54k tokens just to load the spec. If you use several MCPs it adds up really fast.

Verbosity of the output seems orthogonal to the cli vs mcp distinction? When I made mcp tools and noticed a lot of tokens being used, I changed the default to output less and added options to expose different kinds of detailed info depending what the model wants. CLI can support similar behavior.

It has nothing to do with outputs, it’s about the json spec data that goes into the context.
Post reply on HN