Internet Archive

live Data

Internet Archive (archive.org) item search & metadata MCP.

3 tools
0ms auth
free tier 50 calls/day

Tools

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 media

No parameters required.

▶ Try it
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_i

No parameters required.

▶ Try it
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.

No parameters required.

▶ Try it

Test with curl

The gateway speaks JSON-RPC 2.0 over HTTP POST. You can test any pack directly from the terminal.

List available tools
bash 
curl -X POST https://gateway.pipeworx.io/internet-archive/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
Call a tool
bash 
curl -X POST https://gateway.pipeworx.io/internet-archive/mcp \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"search_items","arguments":{}}}'

Use with the SDK

Install @pipeworx/sdk to call tools from any TypeScript/Node project.

TypeScript 
import { Pipeworx } from '@pipeworx/sdk';
const px = new Pipeworx();
const result = await px.call("search_items", {});
ask_pipeworx 
// Or ask in plain English:
const answer = await px.ask("internet archive (archive");