Archives & heritage · MCP server

Internet Archive

Digitised books, periodicals, audio, film and software from archive.org, with full text for scanned texts.

GlobalUnited StatesHosted by Kahubi

Free plan included. No API key needed.

About this source

Search 40M+ items with Lucene syntax (creator, subject, year range, media type), read an item’s metadata and file list, and page through the plain text of scanned books and periodicals. Good for out-of-copyright monographs, government reports and grey literature.

Questions you can ask Internet Archive

Type them into Kahubi’s chat once the source is connected.

Search the collection for records about a named person, place or event and list the reference codes.

What comes back: Matching records with identifiers and links to the originals.

What the assistant can do with it

The 3 tools this server offers to Kahubi. The assistant picks the right one for each question.

  • ia_search

    Search archive.org items.

  • ia_get_item

    Metadata and file list for one item (identifier).

  • ia_get_text

    Plain text of a digitised book/periodical item (its _djvu.txt), paged with offset.

Good to know

  • Hosted by Kahubi. Kahubi runs this server itself so it stays reliable enough for research use.
  • Cited, checkable answers. Results are treated as retrieved material and cited with the source’s own identifiers, so you can open every record the answer relied on.
  • Your files stay private. Only the search the assistant writes for your question is sent to Internet Archive.

More archives & heritage sources

All data sources

Ask Internet Archive your next research question

Connect Internet Archive in one click and get answers that cite their records, next to your own library and drafts. Free to start.