Skip to content
MCP server

MCP Archiveorg

Search inside scanned books, browse the Internet Archive and read Wayback captures

Runs locallyStatus and history
Pricing
Free
Platforms
self-hosted, CLI
Runs
Locally
Version
2.1.0
Listing updated
2 days ago

About MCP Archiveorg

MCP Archiveorg is a free MCP server for books and literature. It runs locally on your machine and is started by your AI client.

Most of the value sits in search_inside, which looks through text that was extracted from page scans by optical character recognition. Results therefore carry the misreadings of that process, and the README notes that no page number is reported because the index states a position that is 1 on nearly every match. A total counts documents, not passages.

The other tools cover the catalogue and the Wayback Machine. search_items filters by media type (texts, movies, audio, image, software, data, web), years and sort order. get_item reads a record with its files and licence, and search_books uses the Open Library index to find books by subject, place, period, person, length or year. list_snapshots and get_snapshot show how an address looked on or near a date.

Requests to archive.org are spaced by a configurable minimum interval (default 1000 ms, floor 500), and the server needs Node 24 or later.

Install

Run in a terminal

claude mcp add mcp-archiveorg -- npx -y mcp-archiveorg

Add to claude_desktop_config.json

{
  "mcpServers": {
    "mcp-archiveorg": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-archiveorg"
      ]
    }
  }
}
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "mcp-archiveorg": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-archiveorg"
      ]
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "mcp-archiveorg": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "mcp-archiveorg"
      ]
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

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

Add to your client's MCP settings (most use this shape)

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

Configuration

  • IA_USER_AGENTIdentify your own client. The project's own identifier is appended, so the Archive can always reach a human.
  • IA_MIN_INTERVAL_MSMinimum milliseconds between requests. Default 1000, floor 500.
  • IA_HISTORY_TIMEOUT_MSDeadline for the capture index, which answers in tens of seconds. Default 60000.
  • IA_LOG_LEVELsilent, error, info or debug. Default error. Logs go to stderr.

Tools this server provides (6)

Taken from the project documentation; the running server may differ.

search_inside
Searches the words inside the archive's scanned documents.
search_items
Searches the catalogue by title, creator, subject and media type.
get_item
Reads one item's record, files and licence.
search_books
Finds books by subject, place, period, person, length or year.
list_snapshots
Lists Wayback Machine captures for an address.
get_snapshot
Reads one capture at or near a date.

What it does

Full-text search
Searches words inside scanned documents, returning excerpts with the matched file.
Catalogue search
Filters items by media type, year range and sort order.
Item records
Reads one item's metadata, files and licence.
Book discovery
Finds books by subject, place, period, person, length or year via Open Library.
Wayback captures
Lists snapshots for an address and reads one near a chosen date.
Polite request pacing
Configurable minimum interval and a custom user agent for the Archive.

Good for

  • Find which scanned books mention a historic place
  • Check the licence and files of an archived item
  • Find French beekeeping books before 1900
  • See how a website looked in March 2001

Pricing

Free

No key or account needed.

MCP Archiveorg FAQ

Is an API key needed?

No. The README says it needs no key and no account.

Does it give page numbers?

No. The index does not report a page of a book, so none is claimed.

Which Node version is needed?

Node 24 or later.

Can I install it without npm?

Yes, through Docker or a downloadable MCP bundle.

Is MCP Archiveorg free?

Yes. MCP Archiveorg is free to use.

How do I add MCP Archiveorg to Claude Code?

Run this command in your terminal: claude mcp add mcp-archiveorg -- npx -y mcp-archiveorg

What are the best alternatives to MCP Archiveorg?

The closest alternatives to MCP Archiveorg are Codebase Memory, XERJ, Claude Code Ultimate Guide, Nautilus Compass Memory and note1.

Alternatives to MCP Archiveorg

  1. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  2. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  3. MCP server for searching the Claude Code Ultimate Guide from any MCP client

    Runs locally
    • Open source
    • 6.5K GitHub stars
    • AI models and LLM tooling
  4. Local-first long-term memory layer for AI agents, served over MCP

    Not checked yet
    • 5 tools
    • Remote
    • Open source
    • 1.3K GitHub stars
    • Knowledge and memory
  5. note1

    MCP server

    MCP server giving AI assistants search and summaries across your note1 meetings

    • 4 tools
    • Remote
    • Free trial
    • 1 GitHub star
    • Productivity