Internet Archive
live ReferenceSearch the Internet Archive, retrieve item metadata, and check Wayback Machine snapshots
3 tools
0ms auth
free tier 50 calls/day
Tools
search
required: query Search the Internet Archive for texts, audio, video, software, and other items. Supports Lucene query syntax.
Parameters
Name Type Description
query req string Search query (e.g., "subject:astronomy", "creator:NASA", "moon landing") limit opt number Number of results to return (1-100, default 20) Try it
Response
get_metadata
required: id Retrieve full metadata for an Internet Archive item by its identifier (the unique ID in the archive.org URL).
Parameters
Name Type Description
id req string Archive.org item identifier (e.g., "principleofrelat00eins", "ApolloMissionsMoonLandings") Try it
Response
wayback_check
required: url Check whether a URL has ever been archived in the Wayback Machine and retrieve the closest available snapshot.
Parameters
Name Type Description
url req string The URL to look up (e.g., "https://example.com/some-page") Try it
Response
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/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/archive/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":2,"method":"tools/call","params":{"name":"search","arguments":{"query": "hello"}}}'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", {"query":"example"}); ask_pipeworx
// Or ask in plain English:
const answer = await px.ask("search the internet archive, retrieve item metadata, and check wayback machine snapshots");