←back to thread

252 points iosifache | 1 comments | | HN request time: 0.217s | source

I was looking around for an MCP server that could connect Anna's Archive to Claude Desktop, as I wanted to be able to search and download books directly through the interface.

I couldn't find any public implementations, so ended up building one myself.

What it does?

- It searches Anna's Archive by keywords. - It downloads books from search results. - It works directly in Claude Desktop through MCP.

Check out the repository's README for detailed installation and configuration instructions.

The code is fully open source and builds run on GitHub Actions for transparency.

I figured I'd share, since I couldn't be the only one wanting this functionality!

Show context
irskep ◴[] No.44515329[source]
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!

replies(4): >>44515432 #>>44518308 #>>44518429 #>>44520766 #
romanovcode ◴[] No.44518308[source]
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.

replies(2): >>44519321 #>>44520863 #
1. andrew_lettuce ◴[] No.44520863[source]
This is pretty naive based on my experience. I find it hard to get the LLM to consistently use the tools defined, so "always" is doing some questionable lifting here. I've had easy better luck with pretty simple, linear workflows, so telling your LLM to "know use this clip tool to..." Might be more effective than an agent that has a bunch of tools and might use the expected one. YMMV