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

31–40 of 85 posts

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

#31

Post by iosifache »

TylerE wrote: post #29
iosifache wrote: post #12

Earlier quoted context omitted.

I just provide a hammer. Users decide whether they're hitting their own nail or the metal one. The comparison might be loose, but the problem is similar to releasing a browser. Do you prevent users from accessing websites you think are malicious or illegal? Or do you delegate that responsibility? I was hesitant about releasing the MCP server as open source software, but I hope (1) it proves useful for others and (2)…

> The comparison might be loose, but the problem is similar to releasing a browser. Do you prevent users from accessing websites you think are malicious or illegal? Or do you delegate that responsibility? I might liken the situation more to releasing a browser and setting thepiratebay as the homepage.

That would imply constantly reminding users of an available action, which isn't the case since the MCP server is just a dormant capability that needs to be triggered.

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

#32

Post by iosifache »

LeratoAustini wrote: post #28
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…

I've downloaded single books several times recently (annas-archive.org in the browser): - search for book - tap a result - see a list of links to download mirrors (under 'slow downloads'), tap a link - get a countdown timer - timer expires, download links appear - click a link, book downloads just like any other download

The waiting part is nonexistent if you have an active donation (which is also required by this MCP server for API access). The fast downloads mean you request a book and start downloading it immediately.

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

#33

Post by iosifache »

btown wrote: post #23
iosifache wrote: post #19

Earlier quoted context omitted.

Cheers, glad you like it! I justified the hours I invested by thinking I could search, download, and explore books directly from Claude Desktop. While the initial steps are achievable with a CLI tool, the integration opens up new possibilities. Some general thoughts: - You’ll find the MCP mental model similar to the API one. - MCP integrations make it easier for non-technical users to access tools that were previousl…

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.

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

#34

Post by thedevilslawyer »

iosifache wrote: post #12
neilv wrote: post #2

> This software does not endorse unauthorized acquisition of copyrighted content and should be regarded solely as a utility. Users are urged to respect the intellectual property rights of authors and acknowledge the considerable effort invested in document creation. How sincere is that statement?

I just provide a hammer. Users decide whether they're hitting their own nail or the metal one. The comparison might be loose, but the problem is similar to releasing a browser. Do you prevent users from accessing websites you think are malicious or illegal? Or do you delegate that responsibility? I was hesitant about releasing the MCP server as open source software, but I hope (1) it proves useful for others and (2)…

IMO, you're needlessly taking a defensive stand. It's ok to take a forward looking stand on how access to knowledge should be.

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

#35

Post by IshKebab »

iosifache wrote: post #32
LeratoAustini wrote: post #28

Earlier quoted context omitted.

I've downloaded single books several times recently (annas-archive.org in the browser): - search for book - tap a result - see a list of links to download mirrors (under 'slow downloads'), tap a link - get a countdown timer - timer expires, download links appear - click a link, book downloads just like any other download

The waiting part is nonexistent if you have an active donation (which is also required by this MCP server for API access). The fast downloads mean you request a book and start downloading it immediately.

"Donation". Let's call it what it is - a subscription.

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

#36

Post by kevindamm »

iosifache wrote: post #15
throwaway314155 wrote: post #5

Earlier quoted context omitted.

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

> I wonder if it would also happily go along with requests for Harry Potter or other copyrighted material? There's no way to protect against this. Anna's Archive doesn't include licence information in their data fields. It would be helpful to integrate with another data source that could warn MCP server users when they're attempting potentially risky actions. Please let me know if you have ideas on how to achieve thi…

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 diligence in finding and contacting the rights holder is considered adequate).

For US works published after 1977 and most works between 1898-1945 the US copyright office has a database:

https://publicrecords.copyright.gov/

but I don't know a good catalog for non-US.

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

#37

Post by 9dev »

thedevilslawyer wrote: post #34
iosifache wrote: post #12

Earlier quoted context omitted.

I just provide a hammer. Users decide whether they're hitting their own nail or the metal one. The comparison might be loose, but the problem is similar to releasing a browser. Do you prevent users from accessing websites you think are malicious or illegal? Or do you delegate that responsibility? I was hesitant about releasing the MCP server as open source software, but I hope (1) it proves useful for others and (2)…

IMO, you're needlessly taking a defensive stand. It's ok to take a forward looking stand on how access to knowledge should be.

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.

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

#38

Post by romanovcode »

irskep wrote: post #17

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.

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

#39

Post by iosifache »

UPDATE:

Following a suggestion from @irskep, I've added CLI command support for the search and download features.

This raised a valid concern - while we're focused on building MCP servers, we shouldn't overlook whether users already have preferred (T/G)UIs available. When they don't exist, we should consider user experience and make our functionality accessible through multiple interfaces beyond just MCP.

https://github.com/iosifache/annas-mcp/releases/tag/v0.0.2

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

#40

Post by iosifache »

IshKebab wrote: post #35
iosifache wrote: post #32

Earlier quoted context omitted.

The waiting part is nonexistent if you have an active donation (which is also required by this MCP server for API access). The fast downloads mean you request a book and start downloading it immediately.

"Donation". Let's call it what it is - a subscription.

[flagged]
Post reply on HN