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

Show HN: MCP server for searching and downloading documents from Anna's Archive

github.com

Post reply on HN
Print view View original

51–60 of 85 posts

Re: Show HN: MCP server for searching and downloading documents from Anna's Archive

#51

Post by mandw »

johnjames87 wrote: post #45

[flagged]

I recently downloaded a number of magazines froma now defunct publication from late eighties. No onesells them and annas archive was the only place i found them. its not exclusivly pirating, its a source for a lot of out of print.

Re: Show HN: MCP server for searching and downloading documents from Anna's Archive

#52

Post by stavros »

profsummergig wrote: post #26

My understanding of Anna's Archive is that one has to download large zip files (>10 Gb) containing thousands of books even if one wants only a single book. Am I correct here? Does this MCP server allow one to download just a single book? I remember once using an IPFS based tool to download a single 200-year-old, out-of-copyright copy of "Last of the Mohicans" from Anna's Archive. It worked, but was very very complica…

You can just go on the website, search for the book you want, and download it. I'd think this is pretty obvious, as if you visit https://annas-archive.org, there are multiple search boxes there that lead directly to downloads.

Re: Show HN: MCP server for searching and downloading documents from Anna's Archive

#53

Post by mhuffman »

totetsu wrote: post #24
thorum wrote: post #3

Interesting project! I’m a little surprised that Claude is willing to call these functions. The demo screenshot is downloading a public domain work, I wonder if it would also happily go along with requests for Harry Potter or other copyrighted material?

Aren’t they all trained on copyrighted material, and lobbying governments to make that legal? Should copyright law only apply to the plebs?

>Aren’t they all trained on copyrighted material, and lobbying governments to make that legal?

Only for them, not for you.

>Should copyright law only apply to the plebs?

In a practical sense, hasn't that been the case for most laws?

Re: Show HN: MCP server for searching and downloading documents from Anna's Archive

#54

Post by jonasdoesthings »

latexr wrote: post #48
romanovcode wrote: post #38

Earlier quoted context omitted.

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.

> 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.

Re: Show HN: MCP server for searching and downloading documents from Anna's Archive

#58

Post by kevindamm »

iosifache wrote: post #43
kevindamm wrote: post #36

Earlier quoted context omitted.

It's worse than you'd expect, there's a sizable subset of works with unknown or uncertain license status. https://wikipedia.org/wiki/Orphan_works_in_the_United_States https://martincopenhaver.github.io/files/orphanworks.pdf [PDF] Estimated 25-50 million books are orphaned works, and their copyright holder may step forward at any time after you've treated it as unlicensed, it's perpetually uncertain (but showing due d…

Ah, wow, thank you for the links and additional context. This is new information to me. > Their copyright holder may step forward at any time after you've treated it as unlicensed. Does this mean that Satoshi can just come and claim that a whole industry is using his/her copyrighted material?

The above is specifically about book copyright on orphaned works.. AFAIK there is no copyrighting of the contents of a blockchain that they could defend (I'm assuming that's what you're referring to). That copyright would hypothetically cover redistribution, which is kind of a necessary aspect of the shared ledger in the first place.

The more appropriate coverage for that would be patents, which protect a process while making its methods public. Since Bitcoin is open and not patented, that isn't a concern either. There are, however, methods of using blockchains that are patented.

Satoshi couldn't come forth and say that all bitcoin is violating a patent, but it's possible that some aspect of other blockchains or some aspect of an application layer built on blockchain is covered by a patent. For more details consult a lawyer specializing in IP law (and btw I'm not a lawyer, in case I accidentally gave that impression).

To complicate things further with patents, be careful about reading patents if you plan on possibly building anything related. If it can be shown that you were aware of a (US) patent that you're violating, then any related suit that comes before you may receive triple the damages that were decided in the case. So, it's very likely that there are some applications violating blockchain-related patents. Someone could suddenly come forward and sue a lot of people who were being willfully ignorant about it.

Hopefully that comes close to answering your question, this space is far too small for all the nuances and I'm not an expert on licenses.

Re: Show HN: MCP server for searching and downloading documents from Anna's Archive

#59

Post by latexr »

throwaway314155 wrote: post #5
thorum wrote: post #3

Interesting project! I’m a little surprised that Claude is willing to call these functions. The demo screenshot is downloading a public domain work, I wonder if it would also happily go along with requests for Harry Potter or other copyrighted material?

Last I checked downloading isn't the issue. It's distributing. Not an expert though.

I think (also not an expert) that depends on jurisdiction. I.e. in some places you can download but not distribute, while in others you can’t even download. Others still turn a blind eye at both (there’s a reason Russian trackers/teams are so prevalent).
Post reply on HN