Internet Archive
pipeworx-io/mcp-internet-archive
Connects Claude to the Internet Archive's vast digital library through the archive.org API. The source doesn't list specific tools, but given the description you're looking at search capabilities across millions of texts, audio recordings, videos, and historical web snapshots, plus metadata retrieval for any item in the collection. Part of the Pipeworx gateway system that lets you query using plain English through ask_pipeworx instead of calling tools directly. Useful when you need to pull historical documents, old software, digitized books, or Wayback Machine snapshots into your workflow. Runs as a hosted service, so no local setup required.
- last updated
- Jun 8, 2026
Sponsors
Readme
mcp-internet-archive
Internet Archive (archive.org) item search & metadata MCP.
Part of Pipeworx — an MCP gateway connecting AI agents to 808+ live data sources.
Tools
| Tool | Description |
|---|
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"internet-archive": {
"url": "https://gateway.pipeworx.io/internet-archive/mcp"
}
}
}
Or connect to the full Pipeworx gateway for access to all 808+ data sources:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English:
ask_pipeworx({ question: "your question about Internet Archive data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Details
- Repository
- github.com/pipeworx-io/mcp-internet-archive
- Website
- pipeworx.io/packs/internet-archive
- Category
- Search & Web Crawling
- Transport
- HTTP
- Registry
- MCP registry, active
