mcp-wayback-machine

Overview

This MCP server provides comprehensive access to the Internet Archive's Wayback Machine through the Model Context Protocol. It features full CDX search functionality, snapshot content retrieval, screenshot listing, snapshot comparison capabilities, and optional authentication for higher SPN2 rate limits. The server implements proper caching strategies with different TTLs for various endpoints, and includes rate limiting with automatic retry handling for 429 responses. It's built with TypeScript and Zod schemas for validation, requiring Node.js 22+.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• save_urlurl, captureScreenshot, captureOutlinks, ifNotArchivedWithin, jsBehaviorTimeout, forceGet, delayWbAvailability

  Archive a URL to the Wayback Machine using the SPN2 API.

  Try:Archive https://example.com to the Wayback MachineTry:Save this URL with a screenshotTry:Archive https://example.com but only if not archived in the last 30 days
• get_archived_urlurl, timestamp, modifier

  Retrieve an archived snapshot's content and metadata.

  Try:Get the latest archived version of https://example.comTry:Retrieve the raw content of https://example.com from 2023Try:Get a screenshot of https://example.com
• search_archivesurl, matchType, from, to, limit, offset, collapse, filter, resolveRevisits, showDupeCount, page, pageSize

  Search the CDX API for archived versions of a URL.

  Try:Find all archived snapshots of https://example.com from 2023Try:Search for archived versions of https://example.com with exact matchTry:Find archives of https://example.com between 2020 and 2022
• check_archive_statusurl

  Check archival statistics for a URL — capture counts, yearly breakdowns, and first/last capture dates.

  Try:Check how many times https://example.com has been archivedTry:Get archival statistics for this URLTry:Find the first and last capture dates for https://example.com
• list_screenshotsurl, limit

  List available screenshots for a URL.

  Try:List all available screenshots for https://example.comTry:Show me the screenshots of this websiteTry:Get screenshots for https://example.com, up to 20
• compare_snapshotsurl, timestampA, timestampB

  Compare two archived snapshots of a URL. Fetches the raw content of both and provides a visual diff URL.

  Try:Compare the oldest and newest snapshots of https://example.comTry:Show differences between these two versions of the websiteTry:Compare https://example.com from 2023 and 2024
• clear_cache

  Clear all cached API responses. Use when fresh data is needed or after saving a new URL.

  Try:Clear the Wayback Machine cacheTry:Refresh all cached dataTry:Forget all cached API responses

Comparable tools

Installation

{
  "mcpServers": {
    "wayback-machine": {
      "command": "npx",
      "args": ["-y", "mcp-wayback-machine"],
      "env": {
        "WAYBACK_ACCESS_KEY": "your-access-key",
        "WAYBACK_SECRET_KEY": "your-secret-key"
      }
    }
  }
}

claude mcp add wayback-machine -- npx -y mcp-wayback-machine

{
  "wayback-machine": {
    "command": "npx",
    "args": ["-y", "mcp-wayback-machine"],
    "env": {
      "WAYBACK_ACCESS_KEY": "your-access-key",
      "WAYBACK_SECRET_KEY": "your-secret-key"
    }
  }
}

FAQ

What authentication is required for this server?

The server works anonymously by default, but setting Internet Archive S3 credentials provides higher rate limits on save operations.

How do I obtain credentials for the Wayback Machine?

Log in to archive.org and visit your S3 API keys page at https://archive.org/account/s3.php to obtain your access and secret keys.

Compare mcp-wayback-machine with