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

Show HN: Iterm-Mcp – AI Terminal/REPL Control for iTerm2

github.com

Post reply on HN
Print view View original

11–20 of 24 posts

Re: Show HN: Iterm-Mcp – AI Terminal/REPL Control for iTerm2

#11

Post by deathmonger5000 »

wrs wrote: post #9
deathmonger5000 wrote: post #6

Earlier quoted context omitted.

Hi, thanks for your comment! I haven't explored that approach. Can you say more? Will using the approach that you suggested support interactive CLI utilities like a REPL? Those are use cases that I definitely want to support with this project.

It’s just in response to “it's not always clear when the job is done”. With shell integration installed, iTerm knows how to separate commands and responses (you can cmd-shift-arrow to move between them, select the entire response with a click, etc.) so I thought it might expose that knowledge. It does that just by putting a distinctive character sequence in the shell prompt, and you could do that directly if needed.…

I wonder how much of what iTerm knows about the current terminal state is exposed. I got it working "good enough for me" and moved on to other pieces of the puzzle. I'm sure what I did could be improved upon quite a bit. I bet you're right that there's additional juice to squeeze out of whatever iTerm exposes.

Re: Show HN: Iterm-Mcp – AI Terminal/REPL Control for iTerm2

#12

Post by nerdjon »

larusso wrote: post #2

A shiver runs down my spine reading „full terminal control“. For me that is a definite no-go. We fight hard to get remote code execution abilities off our system and here we freely invite it. „Hey gpt let me sudo first so you can execute that“

That and the idea of a poorly sanitized log entry or something slipping to the AI and then you have a big problem. Just seems like a security issue waiting to happen.

There was a system not long ago on here for AI automatically running system recovery as triage. I just can’t imagine giving AI any rights to actually run commands without oversight.

I guess good luck explaining why you deleted a database or whatever while diagnosing an app when it decides that the best course of action is to delete and start over or some other really stupid solution.

Re: Show HN: Iterm-Mcp – AI Terminal/REPL Control for iTerm2

#13

Post by v3ss0n »

deathmonger5000 wrote: post #5
pcwelder wrote: post #4

Good work. I wonder if there's really a need for separate write to terminal and read output functions? I was hoping that write command itself would execute and return the output of the command, saving back and forth latency. > and it's not always clear when the job is done I've authored a similar mcp [1] (but without terminal ui) The way I solved it is by setting a special PS1 prompt. So as soon as I get that prompt…

Hi, thanks for the comment! wcgw looks really cool - nice job with it! > I wonder if there's really a need for separate write to terminal and read output functions? I was hoping that write command itself would execute and return the output of the command, saving back and forth latency. I traded back and forth latency for lower token use. I didn't want to return gobs of output from `brew install ffmpeg` when the model…

Why not tail it?

Re: Show HN: Iterm-Mcp – AI Terminal/REPL Control for iTerm2

#14

Post by larusso »

nerdjon wrote: post #12
larusso wrote: post #2

A shiver runs down my spine reading „full terminal control“. For me that is a definite no-go. We fight hard to get remote code execution abilities off our system and here we freely invite it. „Hey gpt let me sudo first so you can execute that“

That and the idea of a poorly sanitized log entry or something slipping to the AI and then you have a big problem. Just seems like a security issue waiting to happen. There was a system not long ago on here for AI automatically running system recovery as triage. I just can’t imagine giving AI any rights to actually run commands without oversight. I guess good luck explaining why you deleted a database or whatever whi…

I‘m part of info sec group in the company I‘m working at and this would get banned right away. Don‘t get me wrong we use and are open to AI and all kinds of tooling ideas to make us more proficient.

Re: Show HN: Iterm-Mcp – AI Terminal/REPL Control for iTerm2

#15

Post by deathmonger5000 »

nerdjon wrote: post #12
larusso wrote: post #2

A shiver runs down my spine reading „full terminal control“. For me that is a definite no-go. We fight hard to get remote code execution abilities off our system and here we freely invite it. „Hey gpt let me sudo first so you can execute that“

That and the idea of a poorly sanitized log entry or something slipping to the AI and then you have a big problem. Just seems like a security issue waiting to happen. There was a system not long ago on here for AI automatically running system recovery as triage. I just can’t imagine giving AI any rights to actually run commands without oversight. I guess good luck explaining why you deleted a database or whatever whi…

> I just can’t imagine giving AI any rights to actually run commands without oversight

We’re 100% on the same page here. No one should ask Claude (or any model) to do something using their terminal and then just walk away. I hope that’s clear from the safety section of what I posted (and in the project README).

Claude REALLY wants to help, and it will go on a journey to the end of the earth to accomplish your task. If you delegate tasks to this tool then you’re going to have to babysit it.

Re: Show HN: Iterm-Mcp – AI Terminal/REPL Control for iTerm2

#16

Post by deathmonger5000 »

v3ss0n wrote: post #13
deathmonger5000 wrote: post #5

Earlier quoted context omitted.

Hi, thanks for the comment! wcgw looks really cool - nice job with it! > I wonder if there's really a need for separate write to terminal and read output functions? I was hoping that write command itself would execute and return the output of the command, saving back and forth latency. I traded back and forth latency for lower token use. I didn't want to return gobs of output from `brew install ffmpeg` when the model…

Why not tail it?

I think you might mean use the tail command? See my other comments about not wanting to change the user’s workflow. I don’t want to get in between the user and their commands in any way. That’s what drove my design decisions.

Would you mind elaborating if I misunderstood what you meant?

Re: Show HN: Iterm-Mcp – AI Terminal/REPL Control for iTerm2

#17

Post by deathmonger5000 »

larusso wrote: post #14
nerdjon wrote: post #12

Earlier quoted context omitted.

That and the idea of a poorly sanitized log entry or something slipping to the AI and then you have a big problem. Just seems like a security issue waiting to happen. There was a system not long ago on here for AI automatically running system recovery as triage. I just can’t imagine giving AI any rights to actually run commands without oversight. I guess good luck explaining why you deleted a database or whatever whi…

I‘m part of info sec group in the company I‘m working at and this would get banned right away. Don‘t get me wrong we use and are open to AI and all kinds of tooling ideas to make us more proficient.

It sounds like iterm-mcp isn’t a tool that would fit in your organization. I’m totally not trying to change that or sell you anything.

I’m curious what your thoughts are around Cursor, Windsurf, etc. Those are IDE’s that provide the model with limited access to the terminal. Where do you feel like those tools and their AI features - terminal access specifically, fall in an org like yours? Are they disallowed due to terminal access or are the limitations of those tools safe enough?

Re: Show HN: Iterm-Mcp – AI Terminal/REPL Control for iTerm2

#18

Post by toprerules »

deathmonger5000 wrote: post #10
toprerules wrote: post #8

Why would you favor this approach over say, a command line tool that can pipe input into and out of a configurable AI backend, fork subprocesses to perform agent based tasks, etc. The amount of tokens is always bounded by what the user chooses to pipe into the tool. The Unix model is battle hardened, time tested approach. This tool seems like it locks you into iTerm2.

> Why would you favor this approach over say, a command line tool that can pipe input into and out of a configurable AI backend, fork subprocesses [...] I think what you're describing is something that's built to perform agent based tasks. iterm-mcp isn't intended to be that. It's intended to be a bridge from something like Claude Desktop to iTerm. The REPL use case is a key thing to understand here. What you're desc…

You can do this without needing a terminal aware tool. There are tools, and it's easy to write one yourself, that tee buffers the output of every command you run, then pipe the last command into your AI tool. You could also easily support N command buffers.

Then you don't need to be locked into using iTerm2.

Re: Show HN: Iterm-Mcp – AI Terminal/REPL Control for iTerm2

#19

Post by deathmonger5000 »

toprerules wrote: post #18
deathmonger5000 wrote: post #10

Earlier quoted context omitted.

> Why would you favor this approach over say, a command line tool that can pipe input into and out of a configurable AI backend, fork subprocesses [...] I think what you're describing is something that's built to perform agent based tasks. iterm-mcp isn't intended to be that. It's intended to be a bridge from something like Claude Desktop to iTerm. The REPL use case is a key thing to understand here. What you're desc…

You can do this without needing a terminal aware tool. There are tools, and it's easy to write one yourself, that tee buffers the output of every command you run, then pipe the last command into your AI tool. You could also easily support N command buffers. Then you don't need to be locked into using iTerm2.

I see what you're saying. Yes, what you described sounds like a much better approach in terms of being terminal agnostic. It would be awesome to have a tool like iterm-mcp that supports any terminal, any OS, etc. iterm-mcp is limited specifically to iTerm.
Post reply on HN