61–70 of 85 posts
What advantage do you get from this being an MCP server rather than simply a command line tool? Genuinely curious, as I'm trying to develop my mental model of when to use one or the other. Lovely project!
A CLI tool, while it can do the same, doesn't do that in a standard way, so if it's a tool not in the agents training set or in its context it won't know how to use the tool.
Why do people keep building servers for such a silly protocol?
It won't know in this case how to use the ssh command line tool.
MCP provides a standard way to tell an AI agent how and when to use tools. So if you had an SSH MCP server, you'd simply plug that in, now your AI agent automagically has SSH capabilities.
What advantage do you get from this being an MCP server rather than simply a command line tool? Genuinely curious, as I'm trying to develop my mental model of when to use one or the other. Lovely project!
COMMAND LINE: You have to instruct your AI what this tool is and what it should be used for. MCP: You paste one command to register the MCP and your AI will always know what it is and where/why it should be used.
Earlier quoted context omitted.
Oh come on. We all know there’s pretty much every novel you’ll find at Barnes&Noble on Anna's Archive as a pirated copy, not just scientific papers. At least be honest; it’s as much a mundane piracy tool as it is a knowledge repository.
I was absolutely saying that. Novels are part of the knowledge too - a scientific paper and a novel have equal weight
[flagged]
Earlier quoted context omitted.
https://neon.com/blog/building-a-cli-client-for-model-contex... might be of interest. An MCP server provides enough metadata and self-documentation that it's quite straightforward to make a MCP-agnostic CLI client that adapts an arbitrary MCP server into a set of flags that allow you to call its explicit tools with explicit arguments - without ever needing to involve an LLM in the mix! You could even have that CLI to…
Agreed on all of this! I'm expecting MCP server creation to be natively supported by API libraries. The abstractions are very similar.
Earlier quoted context omitted.
> COMMAND LINE: You have to instruct your AI what this tool is and what it should be used for. Or —and please bear with me, I know this may sound insane—you call the command-line tool yourself, reliably, fast, with little overhead, just like it has worked for decades. I know, I know, soon most people won’t even know how to unzip their pants without spending unnecessary amounts of electricity and waiting for several s…
I think the goal of this project is not to simplify the use of Annas Archive for humans (as they could just use the Website anyways), but to allow AI "Agents" to automatically source information out of books while researching without requiring user interaction. The LLM's default web-browsing tool probably won't or can't download books from AA while looking for information on a subject. This enables it to do so.
>I justified the hours I invested by thinking I could search, download, and explore books directly from Claude Desktop.
Although you're right that it can be used for use cases like you're describing.
Insane how HN cheers on piracy nowadays, all because it helps them train their LLMs
Insane how HN cheers on piracy nowadays, all because it helps them train their LLMs
Also, HN like the rest of the world was always pro-piracy and getting the fruits of your labor without paying for it.
The only time I’ve seen anti-piracy comments has been been wrt LLM training. Suddenly people pretend to care but it feels performative.