lee/hpr-knowledge-base
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit: HPR Knowledge Base MCP Server

Browse Source 
- MCP server with stdio transport for local use
- Search episodes, transcripts, hosts, and series
- 4,511 episodes with metadata and transcripts
- Data loader with in-memory JSON storage

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Lee Hanken
2025-10-26 10:54:13 +00:00
commit 7c8efd2228
4494 changed files with 1705541 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

71
hpr_transcripts/hpr3977.txt Normal file
View File

@@ -0,0 +1,71 @@
Episode: 3977
Title: HPR3977: Creative Commons Search Engine
Source: https://hub.hackerpublicradio.org/ccdn.php?filename=/eps/hpr3977/hpr3977.mp3
Transcribed: 2025-10-25 18:11:11
---
This is Hacker Public Radio Episode 3,977 for Tuesday 31 October 2023.
Today's show is entitled, Creative Commons Search Engine.
It is hosted by Ahukad and is about five minutes long.
It carries a clean flag.
The summary is, there is a new search engine
for creative commons content.
You are listening to a show from the Reserve Q.
We are airing it now because we had free slots that were not filled.
This is a community project that needs listeners to contribute shows in order to survive.
Please consider recording a show for Hacker Public Radio.
Hello, this is Ahukad,
what's coming you to Hacker Public Radio and another exciting episode.
And this particular one is an emergency show.
So if you're hearing this, it means the queue is low.
And we really need to get some more shows.
So, you know, you've been sitting out there with an idea for something.
It doesn't have to be big.
This is going to be a little quicky one here.
But, you know, we need to have everyone contribute.
So, what I want to do today is I want to talk about something a little kind of a news development a little bit.
And that is that there is a new search engine for creative commons content.
Now, we've talked a lot about creative commons content on Hacker Public Radio.
I know I've talked about using it with GIMP and with Libra Office and similar sorts of things.
And I'm a great believer in creative commons.
Obviously, Hacker Public Radio is as well because Hacker Public Radio is licensed under creative commons.
And all of my content is also licensed under creative commons.
And, you know, if you've been to, I've got several websites.
And, you know, I've got the license very clearly stated at the bottom of each page that says that it is creative commons, you know, attribution.
Now, there are various levels of creative commons licenses.
I'm not going to get into all of that right now.
I have licensed some of my stuff as actually some of the photos and things that I've done.
I have set those as creative commons, what's called creative commons zero, which is essentially public domain.
And, you know, all of the photos I have on Flickr are creative commons licensed.
So, who knows? They may show up in this search engine because Flickr is one of the places they're indexing.
Now, what is this search engine that we're talking about?
It is something called Openverse, link in the show notes, although if you search for Openverse, you'll probably find it equally well.
Right now, as I'm recording this, they claim that they have indexed 700 million creative works.
And so far, all they're working on are stock photos, images, and audio content.
Sources include the Smithsonian, the Cleveland Museum of Art, NASA, Flickr,
Europeana, and the New York Public Library.
But they're looking to expand both the sources, the index, and the types of content.
Now, if you want to see a more extensive list of sources, there's a link in the show notes.
They have a sources page.
Now, they want to go further with this.
They've estimated that there are 2.5 billion creative commons licensed items of all types.
And they're also looking to include video, texts, 3D models, and more.
Now, this Openverse is really the latest incarnation of something that was called CC Search
that was originally created by Creative Commons.
And then in 2019, that was taken over by WordPress, which assumed stewardship for it, and still is.
And they are looking for contributors.
I put a link in the show notes for that.
So if you're interested in contributing to what they do, which, of course, we encourage,
then you can go to that page as well.
So this is a hookah for Hacker Public Radio signing off and encouraging you, as always,
to support free software and creative commons content.
Bye-bye.
You have been listening to Hacker Public Radio at HackerPublicRadio.org.
Today's show was contributed by a HPR listener like yourself.
If you ever thought of recording podcasts, then click on our contribute link to find out
how easy it leads.
Hosting for HPR has been kindly provided by an onsthost.com, the internet archive, and
our syncs.net.
On this advice status, today's show is released under Creative Commons, Attribution 4.0 International
License.