An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Internet Archive Wayback to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Pull historical web snapshots and capture data directly into your AI agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Internet Archive Wayback Machine.

  1. 01

    Check availability

    This capability checks if a specific URL exists in the archive. It returns the most recent snapshot timestamp and the current availability status.

  2. 02

    Get captures by mime type

    This capability retrieves captures filtered by their MIME type. Use it to find specific file types like PDFs, JPEGs, or CSS files within the archive.

  3. 03

    Get captures by status

    This capability pulls captures based on their HTTP status codes. It helps you identify when a site returned specific responses like 200 OK or 404 Not Found.

  4. 04

    Get latest capture

    This capability fetches the most recent preserved version of a URL. It provides the timestamp, status code, and the original URL.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Internet Archive Wayback Machine.

  1. 05

    Get cdx captures

    This capability accesses the CDX server to get a detailed history of captures. Each entry includes the timestamp, original URL, MIME type, status code, and file size.

  2. 06

    Get captures by year

    This capability filters archival captures by a specific four-digit year. It is useful for analyzing how a site looked during a particular time period.

  3. 07

    Get subdomain captures

    This capability finds all archived subdomains for a given domain. It helps you map out the historical footprint of an entire web property.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Internet Archive Wayback Machine.

  1. 08

    Get capture count

    This capability returns the total number of times a specific URL has been archived. Use it to gauge how frequently a page was being tracked.

  2. 09

    Get first capture

    This capability identifies the earliest recorded instance of a URL in the archive. It provides the original timestamp and status code.

  3. 10

    Get captures collapsed

    This capability provides a deduplicated list of captures. It collapses redundant entries to give you a cleaner view of unique page captures.

Real work

What teams actually run

01

Content Verification

Check if a website's messaging was different during a specific period to verify a claim.

02

Digital Forensics

Investigate the history of a domain to find old subdomains or previous owners.

03

Site Evolution Tracking

Compare how a website's structure and assets like CSS or images have changed over years.

04

Broken Link Audits

Use HTTP status filters to find when certain pages on a site stopped working or redirected.

Automate a task

Put Internet Archive Wayback Machine to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Internet Archive Wayback Machine works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Internet Archive Wayback Machine to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

973ms average. Fast in production.

Internet Archive Wayback Machine is checked daily against the live service.

Daily averagePeak 1117ms
Oct 3Today
Fastest day
854ms
Slowest day
1117ms
14-day trend
Stable+1%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Internet Archive Wayback Machine, so you can see the experience inside your AI.

It does not authenticate your account with Internet Archive Wayback Machine. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

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

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Internet Archive Wayback Machine in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Internet Archive Wayback Machine owners hand off.

This MCP is built for professionals who need to verify digital history or recover lost web data. It turns your AI client into a research assistant for web forensics and historical analysis.

  • 01

    Journalists

    They use the agent to verify past claims or recover deleted information from news sites.

  • 02

    Web Developers

    They use the agent to analyze how site designs and implementations have evolved.

  • 03

    Legal Professionals

    They use the agent to preserve and retrieve evidence of website content from specific dates.

  • 04

    Cybersecurity Analysts

    They use the agent to investigate phishing sites and track domain changes.

FAQ

Questions Internet Archive Wayback Machine owners ask.

  • 01

    Do I need an API key for this MCP?

    No. The Internet Archive Wayback Machine is a public service, so no API key or authentication is required.

  • 02

    Which AI clients can use this MCP?

    This MCP works with any compatible client, including Claude, Cursor, Windsurf, and VS Code.

  • 03

    Can I find specific files like PDFs in the archive?

    Yes. You can use the capability to filter captures by MIME type to find specific resources like PDFs, images, or stylesheets.

  • 04

    How can I see when a website first appeared?

    You can use the capability designed to find the first capture, which returns the earliest timestamp for a given URL.

  • 05

    Is the data hosted by Vinkius?

    Yes. Vinkius hosts the MCP and manages the connection, so you don't have to set up any local environments.

  • 06

    How far back does the Wayback Machine go?

    The Wayback Machine has archived web pages since 1996. However, coverage varies significantly. major websites have captures going back 20+ years, while smaller or newer sites may have fewer or no captures. Use get_first_capture to find the earliest archived version of any URL.

  • 07

    Can I find captures that returned 404 errors?

    Yes! Use get_captures_by_status with status_code="404". This returns all archived versions where the page returned a Not Found error. This is useful for tracking when pages were removed or URLs changed structure.

  • 08

    Can I discover all subdomains of a website that have been archived?

    Yes! Use get_subdomain_captures with the base domain (e.g., "example.com"). This returns captures for all subdomains like www.example.com, blog.example.com, api.example.com, etc. It's useful for mapping the full archival footprint of an organization's web presence.

Explore

More in Knowledge Management

Suggestions

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