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

251–260 of 301 posts

Re: When does MCP make sense vs CLI?

#251

Post by giamma »

Imagine asking to your favorite LLM the following: "get the document attached to the most recent email from Joe and then upload it into my document management system in a new folder within archive 'Important', make sure to name the folder based the topic of the document following the naming convention already in place for folders in the same archive"

This could be possible for the average user after activating the appropriate "email" and "document management" MCP servers in their chat interface - maybe following an activation process similar to that of Alexa skills.

How could a regular user achieve the same via CLI? Where would the CLI process be running?

Re: When does MCP make sense vs CLI?

#252

Post by mrinterweb »

bonoboTP wrote: post #176
notepad0x90 wrote: post #168

Earlier quoted context omitted.

Strongly disagree, despite that meaning I'm swimming upstream here. Unlike cli flags, with MCP I can tune the comments for the tool more easily (for my own MCPs at least) than a cli flag. You can only put so much in a cli --help output. The error handling and debugability is also nicer. Heck, I would even favor writing an MCP tool to wrap cli commands. It's easier for me to ensure dangerous flags or parameters aren't…

If you want a validation layer, why not write a cli that wraps the other cli?

This is what I've been working on. I've written a project wrapper CLI that has a consistent interface that wraps a bunch of tools. The reason I wrote the CLI wrapper is for consistency. I wrote a skill that states when and how to call the CLI. AI agents are frequently inconsistent with how they will call something. There are some things I want executed in a consistent and controlled way.

It is also easier to write and debug CLI tooling, and other human devs get to benefit from the CLI tools. MCP includes agent instructions of how to use it, but the same can be done with skills or AGENTS.md (CLAUDE.md) for CLI.

Re: When does MCP make sense vs CLI?

#253

Post by saberience »

giamma wrote: post #251

Imagine asking to your favorite LLM the following: "get the document attached to the most recent email from Joe and then upload it into my document management system in a new folder within archive 'Important', make sure to name the folder based the topic of the document following the naming convention already in place for folders in the same archive" This could be possible for the average user after activating the ap…

OpenClaw and similar agents do that now without using MCP servers.

Re: When does MCP make sense vs CLI?

#254

Post by 3371 »

umairnadeem123 wrote: post #83

> I tried to avoid writing this for a long time, but I'm convinced MCP provides no real-world benefit IMO this is 100% correct and I'm glad someone finally said it. I run AI agents that control my entire dev workflow through shell commands and they are shockingly good at it. the agent figures out CLI flags it has never seen before just from --help output. meanwhile every MCP server i've used has been a flaky process…

I'll just disagree with an example: Codex on Windows.

They are known to be very inefficient using only Powershell to interact with files, unless put in WSL. They tend to make mistakes and have to retry with different commands.

Another example is Serena. I knew about it since the first day I tried out MCP but didn't appreciate it, but tried it out again on IDEs recently showed impressive result; the symbolic tools are very efficient and helps the agents a lot.

Re: When does MCP make sense vs CLI?

#256

Post by vrosas »

D-Machine wrote: post #238
seemaze wrote: post #223

Earlier quoted context omitted.

> dump a large payload into Claude's filesystem and let him figure it out I just realized I never thought of Claude as ‘him’, usually I think of Claude as ‘it’..

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?

Re: When does MCP make sense vs CLI?

#257

Post by shusaku »

> This is where the gap gets wide. CLIs compose. I can pipe through jq, chain with grep, redirect to files. This isn’t just convenient; it’s often the only practical approach.

Unix style composability is a beautiful thing. But when was the last time you installed a set of tools that actually worked together like this? It only works for simple tools. And you can already connect all the simple ones you want (grep, awk, etc) through the file system.

Re: When does MCP make sense vs CLI?

#258

Post by lidn12 »

dnautics wrote: post #39

what honestly is the difference between an mcp and a skill + instructions + curl. Really it seems to me the difference is that an mcp could be more token-efficient, but it isn't, because you dump every mcp's instructions all the time into your context. Of course then again skills frequently doesn't get triggered. just seems like coding agent bugs/choices and protocol design?

[dead]

Re: When does MCP make sense vs CLI?

#259

Post by bonoboTP »

bspammer wrote: post #249
bonoboTP wrote: post #175

Earlier quoted context omitted.

Even if the help isn't great, good coding agents can try out the cli for a few minutes and write up a skill, or read the sources or online docs and write up a skill. That takes the spot of the --help if needed. I found that I can spare quite a lot of time, I don't have to type up how to use it, if there is available info about it on the web, in man pages, in help pages, or the source is available, it can figure it ou…

Using the source code to ask questions about poorly documented features in projects you have no experience is my favourite thing that LLMs make possible (of course you could do this before but it would take way, way more time). There are so many little annoyances that I’ve been able to patch and, thanks to NixOS, have the patched software permanently available to me. In fact NixOS + LLMs feels like the full promise o…

Yes, the idea that you can meaningfully modify the program for your own purposes (one of Stallman's four freedoms) was quite unrealistic except for the most skilled and invested among users. LLMs change this. I mean, as long as you use open models. I fear that in the future, corporate models may start to refuse building software like this that is inconvenient for them. Like possible future-Gemini saying, "oh I see you're patching chromium to continue working with adblockers, this is harmful activity, I cannot help you and reported your account to Google. Cease and desist from these plans or you lose your Gmail!"

Today is the honeymoon phase, enshittification will come later when the pie stops growing and the aspect of control comes more into focus.

It's just too good to be true. Most people still don't know that you can now do what you just described. Once people in the suits understand this, the propaganda will start about how unsafe this all is and that platforms must be locked down at the hardware level, subscriptions cut off if building unapproved software etc.

Re: When does MCP make sense vs CLI?

#260

Post by benkaiser »

One key aspect that is missed here, is mobile users.

iOS don't have a CLI, Android phones... kinda have a CLI, but it's not really usable by all apps / universal like it is on desktop.

I've been putting together a MCP client for mobile recently [1] since to me it seems apparent that Remote MCP is a great utility but none of the major players offer it without a paid subscription.

As other commenters have mentioned, the use case here is really not for software developers, it's for everyone else. It's bringing that agentic loop to do all those "personal assistant" type things in a connected way with all of your services. We're not there yet, but maybe some day.

[1] https://github.com/benkaiser/joey-mcp-client

Post reply on HN