• SUBDOMAINS
  • FILES
  • TIMELINE
  • HUMAN

How to audit historical site structure with your AI

Connect to the Internet Archive to pull historical snapshots and metadata. Your AI then organizes these archives into a clear map of your domain's past.

Ask AI about this page

Short answer

How can I audit my site's historical structure with AI?

Your AI uses archival metadata to identify old subdomains, forgotten file types, and previous URL patterns. You get a complete map of your domain's evolution through historical snapshots. This breakdown shows you how to pull that data and organize it.

Audit outcomes

Where your audit data lands.

The AI processes raw archival snapshots into these specific categories.

SUBDOMAINS

Old subdomain maps

The AI identifies every subdomain that has ever been captured. You'll see exactly which subdomains were active in previous years.

FILES

Specific file discovery

The AI filters snapshots to find specific MIME types. This helps you find old PDFs, images, or scripts that are no longer linked but still exist in the archive.

TIMELINE

Capture history logs

The AI pulls a chronological list of all captures for a domain. You get a clear timeline of when your site was most active in the archives.

HUMAN

Manual site review

The AI provides the metadata, but you decide which old files are safe to re-index or which old subdomains should stay dead.

The workflow

What your AI does when the request arrives.

The AI acts as a bridge between your chat interface and the Internet Archive's massive database.

  1. Identify subdomains

    The AI scans the archive to find every subdomain associated with your primary domain. This reveals the full breadth of your historical footprint.

    get_subdomain_captures

  2. Filter by file type

    The AI looks through the metadata to isolate specific file formats like PDFs or ZIP files. This is useful for finding legacy assets.

    get_captures_by_mime_type

  3. Build a capture list

    The AI pulls a raw list of all historical captures for a specific URL. This provides the foundation for a chronological audit.

    get_cdx_captures

  4. Synthesize the map

    The AI takes the raw metadata from the previous steps and organizes it into a readable report or a structured list for your review.

    get_cdx_captures

Try it

Copy these to start.

Use these prompts to kick off your audit.

Starting points

Replace the domain names and file types with your actual targets.

Internet Archive Wayback Machine Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_hnm6MKLSX94NqzQjsRaRbJo66cdvIxnhQfEOtu5s/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Internet Archive Wayback Machine capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "internet-archive-wayback-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_hnm6MKLSX94NqzQjsRaRbJo66cdvIxnhQfEOtu5s/mcp"
    }
  }
}
Copy into chat04

  • List all subdomains captured for example.com to see the historical footprint.

  • Find all PDF files captured for mydomain.com in the last five years.

  • Show me a timeline of all captures for old.site.com.

  • Identify any old subdomains for company.org that were active in 2015.

  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Start here

Connect Internet Archive once, then ask.

Just click to connect. Your credentials stay encrypted, and you can immediately start asking your AI about archival data.

Connect Internet Archive to your AI

FAQ

How this task behaves.

  • 01

    Can the AI delete old files from the Internet Archive?

    No. The AI only has permission to read metadata and capture information. It cannot modify or delete anything in the archive.

  • 02

    Can the AI see the actual content of a webpage?

    No. The AI uses the metadata and capture lists to identify what exists. It does not scrape or read the full HTML content of the snapshots.

  • 03

    Does this work for any domain?

    Yes, as long as the domain has been crawled and captured by the Internet Archive.

  • 04

    Can the AI update my live website based on these findings?

    No. The AI only interacts with the Internet Archive. Any changes to your live site must be done by you manually.

  • 05

    How does the AI find specific file types?

    The AI uses the MIME type metadata provided by the archive to filter the list of captures.

  • More questions about Internet Archive? See everything the Internet Archive Connector can do

Connect Internet Archive Wayback Machine to Claude, Cursor, ChatGPT & more