# Internet Archive Metadata MCP for AI Agents AI Agent Connect > Internet Archive Metadata gives your AI agent direct access to the massive library of the Internet Archive. Instantly pull file lists, user reviews, download stats, and full metadata for any archived item. It turns the archive into a searchable database for your agent, letting you move from a URL to deep data in seconds. No more clicking through pages; just get the facts. ## Overview - **Category:** knowledge-management - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_g2DPM5mFBk8GGzj6mnIa4BLp6pdztmnUduZeaSbN/ai-agent-connect - **Tags:** digital-archiving, metadata-extraction, library-science, open-data, file-retrieval, historical-records ## Description You're looking for a way to pull data from the Internet Archive without the headache of manual browsing. This Connector lets your AI agent do the heavy lifting by grabbing metadata, file lists, and community feedback directly from the source. Instead of clicking through multiple tabs to see what's available or checking how many people have downloaded a specific item, you can just ask your agent to do it for you. It turns a massive, complex library into a structured data source you can query on the fly. Vinkius makes it easy to get this connected so you can focus on the actual research rather than the navigation. Whether you're looking for specific file formats or trying to see how an item has changed over time, this tool puts that information right in front of you. Imagine being able to audit thousands of archived entries to find specific license types or creator names without ever opening a browser. You can ask about the technical storage details for a specific upload or see how many people are actually interacting with a piece of media. It takes the friction out of exploring the world's largest digital warehouse, providing you with a direct line to the facts you need for your project. ## Tools ### get_metadata_only Grab basic info quickly without the extra file or review data. This is the best way to get a fast lookup for simple queries. ### get_parents See the higher-level categories for better context. This helps you understand the broader categorization structure of an item. ### get_reviews Fetch user ratings and text reviews from the community. See what other people are saying about the archived content. ### get_server_info Check the hosting location and storage details for a specific item. This is useful for technical diagnostics and location tracking. ### get_collections Find out which specific categories an item belongs to. This helps you understand how the archive organizes its content. ### get_derivatives See auto-generated files like thumbnails or OCR text. This shows you what processed versions of the original upload are available. ### get_files Get a full list of downloadable files and their sizes. You can quickly see which formats are available for an item. ### get_metadata Pull all primary details like title, creator, and subjects. This provides a complete overview of the item's information. ### get_history View the timeline of changes made to an archived item. Use this to track how the content or metadata has evolved. ### get_stats See how many people have downloaded or viewed the item. Use this to measure the popularity and reach of specific content. ## Prompt Examples **Prompt:** ``` Tell me about the big_buck_bunny item. ``` **Response:** ``` Here is the metadata for big_buck_bunny: - **Creator**: Blender Foundation - **Date**: 2008 - **Type**: Animation/Short film - **Duration**: 10 minutes - **Collection**: Community Video - **Available formats**: MP4, OGV, and various archival formats. ``` **Prompt:** ``` What files are available for gutenberg_etext1? ``` **Response:** ``` I found 8 files for gutenberg_etext1: - gutenberg_etext1.txt (plain text, 1.2 MB) - gutenberg_etext1.epub (EPUB, 800 KB) - gutenberg_etext1.mobi (MOBI, 900 KB) - gutenberg_etext1.pdf (PDF, 2.1 MB) - Multiple other metadata files. ``` **Prompt:** ``` Are there any reviews for nasa_apollo11? ``` **Response:** ``` I found 23 reviews for nasa_apollo11. - **Average Rating**: 4.8/5 stars - **Top Review**: 'Incredible historical footage. The quality restoration is remarkable. A must-watch for anyone interested in space exploration.' from user spacefan42. ``` ## Capabilities ### Pull complete item metadata Get every detail from the creator to the license in one go. ### List all downloadable files See every format and size available for an archive entry. ### Check community reviews See what other people are saying about specific items. ### View download statistics See how many people have downloaded or viewed an item. ### Track modification history See how an item has changed over time. ### Find parent collections See the broader hierarchy an item belongs to. ### Get server info Identify exactly where the files are hosted for technical checks. ## Use Cases ### Finding high-quality media versions A historian needs to find all MP4 versions of a specific documentary. They ask the agent to list files and identify the highest quality version. ### Verifying archive updates A librarian wants to know if a collection has been updated. They use the history tool to see recent modification dates. ### Measuring content reach A researcher needs to see if a book is popular. They ask for the download stats to see its reach in the community. ### Contextual content discovery A curator wants to find related content. They check the parent collections to see where the item sits in the archive's hierarchy. ## Benefits - Get full item details instantly using get_metadata to skip the manual browsing. - Identify the best file formats quickly with get_files to avoid downloading the wrong version. - Measure item popularity and reach using get_stats for data-driven research. - Understand the archive's hierarchy using get_parents to find related content easily. - Verify item changes over time with get_history to ensure your data stays current. - See what the community thinks by pulling review text with get_reviews. ## How It Works The bottom line is you get organized data from the Internet Archive without ever leaving your chat window. 1. Connect this Connector to your AI client through the Vinkius dashboard. 2. Give your agent the unique identifier from the Internet Archive URL. 3. Ask for specific details like file sizes, review scores, or collection info. ## Frequently Asked Questions **Can Internet Archive Metadata help me find specific files?** Yes, it lists every downloadable file, its format, and its size so you know exactly what's available for an item. **How do I get stats for an item?** You can see how popular an item is by pulling its download and view counts directly through the agent. **Can I see reviews for an archive item?** Yes, it pulls community ratings and review text so you can see what other people think of the archived content. **Does this tool help with library science?** It's great for librarians who need to see parent collections and modification histories for better organization. **Can I see how an item has changed over time?** Yes, you can track modifications to see when and how an archive entry was updated. **How do I find which collections an item belongs to?** The agent can automatically pull a list of every collection associated with a specific archive identifier. **How do I get the identifier for an item?** The identifier is the unique string in the item's URL. For example, from https://archive.org/details/big_buck_bunny, the identifier is "big_buck_bunny". You can also get identifiers from search results using the ia-search-mcp server. **What file formats are typically available?** It depends on the item type. Texts often have PDF, EPUB, MOBI, plain text, and Daisy formats. Movies have MP4, OGV, and archival formats. Audio has MP3, OGG, and FLAC. The get_files tool shows all available formats for each item. **Can I see who reviewed an item?** Yes! Use the get_reviews tool. It returns the reviewer's username, star rating (1-5), review text, and review date. Not all items have reviews — community-contributed items tend to have more user feedback.