Wraps the Internet Archive APIs so you can search and retrieve historical web snapshots, books, videos, and other archived content without dealing with authentication. Part of the larger Pipeworx gateway ecosystem that bundles 673+ data sources, but you can run this standalone if you only need Archive access. The real hook here is the ask_pipeworx natural language interface that translates plain English questions into the right API calls instead of you manually constructing tool parameters. Useful when you're building agents that need to reference historical web content, verify when something was published, or pull from Archive's massive public domain collection. Free to use, no API keys required.
Archive MCP — wraps the Internet Archive APIs (free, no auth)
Part of Pipeworx — an MCP gateway connecting AI agents to 673+ live data sources.
| Tool | Description |
|---|
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"archive": {
"url": "https://gateway.pipeworx.io/archive/mcp"
}
}
}
Or connect to the full Pipeworx gateway for access to all 673+ data sources:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Instead of calling tools directly, you can ask questions in plain English:
ask_pipeworx({ question: "your question about Archive data" })
The gateway picks the right tool and fills the arguments automatically.
MIT