internet-archive 3 tools

MCP server exposing 3 tools for internet-archive.

Endpoint

This URL is a JSON-RPC 2.0 endpoint over HTTP. Issue POST requests with a JSON-RPC body. Browsers and search crawlers land here on GET.

POST https://gateway.pipeworx.io/internet-archive/mcp
Content-Type: application/json

{"jsonrpc":"2.0","id":1,"method":"tools/list"}

search_items — Search Internet Archive (archive.org) items by Lucene-style query. Finds archived books, audio, video, software, and images — e.g. "apollo", "creator:NASA", "grateful dead". Optionally filter by mediatype. Returns identifier/title/creator/year/mediatype/downloads. NOTE: archive.org items, NOT Wayback Machine web-page snapshots. Keyless.
get_metadata — Fetch an Internet Archive item's metadata by identifier: title, creator, description, date, mediatype, subject, publisher, language, plus file count and total size. Returns a details_url. Use search_items first to find an identifier. Keyless.
list_files — List the downloadable files for an Internet Archive item: name, format, size, and a constructed download_url. Use search_items / get_metadata first to find an identifier. Keyless.

Code samples (curl / TypeScript / one-click client install), schemas, and the live playground are on the pack page:
https://pipeworx.io/packs/internet-archive/

Pipeworx is an open MCP gateway connecting AI agents to live data. pipeworx.io