# Internet Archive MCP for AI Agents AI Agent Connect > Internet Archive MCP lets you search 40 million+ items in the world's largest digital library. Use it to find old books, films, audio recordings, and software, or check website snapshots using the Wayback Machine. It connects your AI client directly to historical data without needing an API key. ## Overview - **Category:** brain-trust - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_QUjUHEHPZMANuxID12PQUElpX6vKZVzoTBAKfHml/ai-agent-connect - **Tags:** digital-library, wayback-machine, archival-data, metadata-search, historical-records, open-access ## Description The Internet Archive MCP connects you to the world's largest digital library, giving you a direct line to over 40 million books, films, and historical web snapshots. Usually, finding this kind of data means jumping between dozens of tabs, fighting with clunky filters, and manually tracking down download links. This Connector changes that by letting your agent do the heavy lifting. You can just ask for a specific decade of science fiction movies or a specific author's complete bibliography, and the agent pulls the metadata, file types, and even community reviews instantly. It handles the complex query syntax for you, whether you're looking for a specific collection like NASA images or a specific media type like classic software. It's built to be a direct line into the world's digital memory. Because Vinkius makes it so easy to manage these connections, you can move from a broad search across the entire archive to a specific file listing for a single item in one conversation. It's about getting to the source material faster, whether you're a historian looking for primary sources or a developer hunting for abandoned software. You can even verify if a website still exists or see what it looked like years ago with a few simple prompts. ## Tools ### search_by_collection Browse specific curated sets like the NASA collection or Project Gutenberg. This lets you dive into organized groups of related items. ### search_by_creator Find every work associated with a specific author, director, or organization. Use this to see the full catalog of a specific person's work. ### search_by_date_range Find content from specific eras by combining a query with year filters. This helps you isolate items from a specific decade or time period. ### search_by_mediatype Filter results to show only books, movies, audio, software, images, or datasets. Use this when you want to narrow your search to a specific format. ### get_item_files See all available download formats and file sizes for a specific archive item. This helps you know what files are ready for you to grab. ### get_item_metadata Get the full title, creator, description, and license details for a specific item. This is useful for getting accurate citations and item details. ### get_item_reviews Read community ratings and feedback to judge the quality of an archived item. Use this to see what other people thought of the content. ### get_views_stats Check the popularity and geographic reach of a specific archived piece of content. This helps you see how much attention an item has received. ### search Run broad queries across the entire archive using complex syntax like AND, OR, and NOT. This is the primary way to find items across all media types. ### wayback_availability Check if a specific URL has a snapshot and get the most recent timestamp. Use this to see if a page has been preserved in the past. ## Prompt Examples **Prompt:** ``` Find some public domain movies from the 1940s that are available in MP4 format. ``` **Response:** ``` I found several public domain films from the 1940s available in MP4 format: | Title | Year | Collection | Format | | :--- | :--- | :--- | :--- | | **It's a Wonderful Life** | 1946 | Prelinger Archives | MP4 | | **The Scarlet Letter** | 1934 | Community Films | MP4 | | **WWII Newsreel** | 1942 | News Archive | MP4 | Would you like more details on any of these titles? ``` **Prompt:** ``` Has the website for 'old_news_site.com' been archived? If so, what's the most recent date? ``` **Response:** ``` Yes, the website has been archived. * **Closest Snapshot:** January 1, 2024 * **Access Link:** https://web.archive.org/web/20240101120000/https://example.com The Wayback Machine has captured this page multiple times over the years. ``` **Prompt:** ``` Show me some NASA images from the Apollo missions. ``` **Response:** ``` I found over 185,000 NASA items in the archive. Here are some highlights from the Apollo collection: * **Apollo Mission Photographs** * **Hubble Space Telescope Images** * **Satellite Imagery** * **Astronaut Training Footage** The items span from the 1960s to the present day. Would you like to narrow these down by a specific mission or decade? ``` ## Capabilities ### Search 40 million items across multiple media types Find books, movies, audio, software, and images in one place. ### Pull complete metadata for specific archived items Get titles, creators, descriptions, and licenses instantly. ### Check the Wayback Machine for historical website snapshots See if a URL was archived and find the most recent timestamp. ### Filter results by specific historical date ranges Isolate content from specific decades or years with easy filters. ### Browse curated collections like the Prelinger Archives Dive into specific groups like NASA images or Project Gutenberg. ### Get user reviews and popularity statistics for items See what the community thinks and how many views an item has. ## Use Cases ### Finding public domain assets A content creator is looking for public domain films from the 1940s for a new project. They ask their agent to find suitable titles, and the agent returns a list of films with their available formats like MP4 and OGV. ### Verifying website changes A journalist needs to see how a specific company's landing page looked three years ago to verify a past claim. They ask the agent to check the Wayback Machine for that URL and get the most recent snapshot date. ### Academic research A student is writing a thesis and needs a complete bibliography of a specific author. They ask the agent to find all works by George Orwell and get a list of titles, creators, and dates from the archive. ### Finding niche software A developer wants to find abandonware or classic PC games from the 1990s for a preservation project. They ask the agent to search the archive for those specific terms and get a list of available software. ## Benefits - Skip the manual search: Use search and search_bymediatype to find exactly what you need without clicking through endless pages. This saves you from navigating clunky archive menus. - Verify web history: Use wayback_availability to instantly see if a URL was captured and when it was last seen online. It's a huge help for fact-checking deleted content. - Get deep metadata: Pull full details, licenses, and subjects with get_item_metadata to ensure your citations are accurate. You get everything in one place. - Explore curated archives: Use search_by_collection to jump straight into specific sets like NASA images or the Prelinger Archives. It makes finding niche groups much faster. - Check item quality: Use get_item_reviews and get_views_stats to see what the community thinks before you spend time on a download. You can gauge popularity in seconds. - Filter by era: Use search_by_date_range to isolate content from specific decades for more accurate historical research. This narrows down the results perfectly. ## How It Works The bottom line is you get instant, conversational access to the world's largest digital library without managing API keys. 1. Subscribe to the Internet Archive MCP on Vinkius. 2. Connect your preferred AI client to the Vinkius catalog. 3. Ask your agent to find specific archives, dates, or URLs. ## Frequently Asked Questions **Can I use the Internet Archive MCP to find old books?** Yes, you can search 40 million+ items including books, movies, and audio files directly through your AI client. **Does the Internet Archive MCP require an API key?** No, this Connector uses the public archive, so you don't need to sign up for anything or manage keys. **Can I use this to check old website versions?** Yes, the Connector includes a tool to find snapshots from the Wayback Machine for any URL you provide. **Is the Internet Archive MCP good for finding public domain content?** It's perfect for that. You can filter by media type and date to find safe assets for your projects. **Can I see the file formats for archived items?** Yes, the Connector can pull a full list of available formats like PDF, MP4, and MP3 for any specific item. **How does the Internet Archive MCP handle complex searches?** It supports advanced syntax like AND, OR, and NOT, plus field-specific searches like subject:world war 2. **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 Connector doesn't support). **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. **How can I use the Wayback Machine to find archived websites snapshots?** Use the wayback_availability tool 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. **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.