MCP Archiveorg

What mcp-archiveorg does

mcp-archiveorg exposes search and retrieval tools for three related collections. Internet Archive tools cover catalogue items, OCR text inside scanned books and documents, item metadata, and downloadable files. Open Library search helps identify works by title, author, subject, place, period, person, publication year, or page count. Wayback tools locate captures of web pages and list the dates held for an address.

A typical workflow starts with a search and follows an identifier into get_item. For full-text research, search_inside returns passages and the item or container that holds them. For historical web research, get_snapshot finds the capture nearest a requested moment, while list_snapshots shows the available capture dates.

How it works

The server communicates with an MCP client through the command launched by npx, or through the supplied Docker image or MCP bundle. Its remote requests require outbound HTTPS access to archive.org, web.archive.org, and openlibrary.org when run in Docker. No credentials, account, volume, or listening port are required.

Search results are paginated. search_inside searches OCR output, so excerpts can contain recognition errors. Quoted queries keep words together, while unquoted words are matched separately; accent, case, and punctuation differences are folded by the index. Its total value counts matching documents, not phrase occurrences, and the result does not identify a printed page number.

Wayback results describe captures rather than page contents. get_snapshot reports how far the selected capture is from the requested date and may return a neighbouring URL form. list_snapshots is paged with a cursor and can take tens of seconds for heavily archived addresses.

Setup and configuration

Install with the standard MCP command:

{
  "mcpServers": {
    "archiveorg": {
      "command": "npx",
      "args": ["-y", "mcp-archiveorg"]
    }
  }
}

Node.js 24 or later is required. Claude Code can add it with claude mcp add archiveorg -- npx -y mcp-archiveorg. Cursor and VS Code have installation links, and the same standard configuration works with Claude Desktop.

Docker users can run ghcr.io/smeet666/mcp-archiveorg with an interactive standard input stream and no TTY. The project also publishes an .mcpb bundle that can be opened by clients supporting MCP bundles; the bundle includes its dependencies and needs no npm setup. No environment variables need to be configured.

Tools and capabilities

• search_inside searches OCR text in digitised books, newspapers, and documents. It returns excerpts, identifiers, source URLs, and the file containing a match.
• search_items searches Internet Archive catalogue metadata across texts, films, audio, images, software, datasets, and web material. Filters include media type, date range, and sort order.
• get_item reads an item by identifier. Optional sections provide basic metadata, files, or the complete metadata record; file count and total bytes are always included.
• search_books searches Open Library works using free text or criteria such as subject, place, time, person, first-publication year, and page count. Results can include up to three archive identifiers and the number of scans.
• get_snapshot finds the Wayback capture closest to a supplied date, or the most recent capture when no date is given.
• list_snapshots lists archived captures oldest first, with dates, captured addresses, and a cursor for retrieving later results.

Limitations and notes

OCR matches reflect the text recognition layer rather than a verified transcription. A hit inside a bundled item may describe the container; inspect matched_file to identify the document that actually matched. Catalogue dates are depositor-entered fields, while Open Library publication years are derived from edition records, so either can require verification in the returned record. A Wayback capture records when a crawler visited a URL, not exactly when the page changed, and finding a capture does not return the page body.