An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Internet Archive to ChatGPT, Claude and Gemini

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 data and media 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.

  1. 01

    Search by creator

    Find all works produced by a specific author, director, or organization. This capability matches the creator name against item metadata to pull complete collections.

  2. 02

    Get item reviews

    Pull community ratings and text reviews for an archived item. This helps your agent understand how people have received a specific work.

  3. 03

    Get views stats

    Check the popularity of an item through total view counts and geographic data. Use this to see how much reach a specific piece of content has.

  4. 04

    Search by date range

    Find historical content from a specific era by providing a start and end year. This is how you isolate media from a particular decade or time period.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Internet Archive.

  1. 05

    Search by mediatype

    Filter your search results by specific formats like movies, audio, software, or images. This ensures your agent only looks at the media type you actually want.

  2. 06

    Wayback availability

    Check if a URL has been preserved by the Wayback Machine. It returns the most recent archived snapshot and the link to view it.

  3. 07

    Get item files

    List all downloadable files associated with an item. This shows you exactly which formats like EPUB or MP4 are available for a specific piece of media.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Internet Archive.

  1. 08

    Get item metadata

    Retrieve full details for a specific item, including descriptions, subjects, and license info. Use this to get the complete context of a file before you use it.

  2. 09

    Search

    Search the entire Internet Archive for books, videos, audio, and more. Use complex syntax like AND, OR, or field-specific queries to find exactly what you need.

  3. 10

    Search by collection

    Browse through curated groups like the Prelinger Archives, NASA images, or Project Gutenberg. It targets specific subsets of the library for more focused discovery.

Real work

What teams actually run

01

Fact Checking

Use the Wayback Machine to see what a company's website looked like years ago to verify claims.

02

Media Sourcing

Find public domain video clips or music for use in a video essay or creative project.

03

Academic Research

Locate specific historical documents or books from a particular decade for a paper.

04

Software Preservation

Search for and identify classic software or abandonware for emulation or study.

Automate a task

Put Internet Archive 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 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 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.

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, so you can see the experience inside your AI.

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

Internet Archive Connector

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

Connector linkhttps://edge.vinkius.com/vk_preview_QUjUHEHPZMANuxID12PQUElpX6vKZVzoTBAKfHml/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 capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "internet-archive-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_QUjUHEHPZMANuxID12PQUElpX6vKZVzoTBAKfHml/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 in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Internet Archive owners hand off.

This MCP is built for anyone needing to pull primary source data or historical media into an AI-driven workflow.

  • 01

    Researchers

    They hand off the task of finding rare books and academic papers to the agent.

  • 02

    Journalists

    They use the agent to verify old web content via the Wayback Machine.

  • 03

    Content Creators

    They task the agent with finding public domain films and music for projects.

  • 04

    Developers

    They use the agent to locate classic software and historical computing files.

FAQ

Questions Internet Archive owners ask.

  • 01

    Do I need an API key for this MCP?

    No, this MCP uses public access, so no API key or registration is required.

  • 02

    Can I download files through the AI?

    The agent provides the direct download links and file formats, such as PDF or MP4, which you can then use.

  • 03

    Which AI clients can use this?

    You can use this with any MCP-compatible client, including Claude, Cursor, and Windsurf.

  • 04

    How does the Wayback Machine work here?

    The agent uses the Wayback Machine capability to check if a URL has been archived and provides the closest available snapshot.

  • 05

    Is the data hosted by Vinkius?

    Yes, Vinkius hosts the MCP and manages the connection so it is ready to use immediately.

  • 06

    Is any authentication required to use the Internet Archive API?

    No! All search, metadata, and Wayback Machine features are completely free and public. no API key or account needed. You can search 40M+ items, get item details, and check archived URLs immediately. Authentication is only required if you want to upload content (which this MCP server doesn't support).

  • 07

    How do I find and download files from an archived item?

    First, use search to find items matching your query and note the identifier (e.g., "big_buck_bunny"). Then use get_item_files to see all available files with their formats (PDF, MP4, MP3, etc.). Files can be downloaded directly from: https://archive.org/download/{identifier}/{filename}. Many items offer multiple formats for the same content.

  • 08

    How can I use the Wayback Machine to find archived websites snapshots?

    Use the wayback_availability capability with any full URL (e.g., "https://example.com"). It returns the closest archived snapshot with its timestamp. The archived page can be viewed at: https://web.archive.org/web/{timestamp}/{original_url}. Note: Not all URLs are archived. the Wayback Machine selectively crawls and saves web pages.

  • 09

    What collections are available in the Internet Archive?

    Major collections include: Prelinger Archives (ephemeral films), Project Gutenberg (free ebooks), NASA (space images and videos), TV News Archive, FedFlix (government films), Open Source Movies, Netlabels (independent music), Software Library (classic games and apps), American Libraries, Biodiversity Heritage Library, and thousands of community collections. Use search_by_collection to explore any collection.

Explore

More in Brain Trust

Suggestions

Connect Internet Archive to Claude, Cursor, ChatGPT & more