Internet Archive MCP. Access 40M+ historical media records in one chat.
Internet Archive MCP connects your AI agent to the world’s largest digital library, accessing 40 million+ items in one chat session. Search everything—books, films, music, software, and historical web pages via the Wayback Machine—using natural conversation instead of complicated search forms.
Give Claude and any AI agent real-world access
The agent searches pre-curated categories like Project Gutenberg ebooks or NASA images without needing to specify the collection name.
It checks if a given URL has been archived, returning the closest available snapshot date and link through the Wayback Machine.
You can narrow searches down to items created by an author or organization, or filter results only for movies, audio, or texts.
The agent retrieves full metadata—including subjects, file formats, and download statistics—for any found item.
It pulls user ratings and review texts from the community to help you assess an item's quality or relevance.
Ask an AI about this
Waiting for input…
What AI agents can do with Internet Archive: 10 Tools for Archival Research
Use these specific tools to narrow down your search, check metadata, find file formats, or verify the history of a URL.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using Internet Archive MCPSearch By Collection
Search for items within specific curated categories like Project Gutenberg ebooks or Prelinger Archives.
Search By Creator
Find all content created by a particular author, organization, or artist name.
Search By Date Range
Filter results to find content from specific historical eras or decades using start...
Search By Mediatype
Limit your search to only one format, such as movies, audiobooks, images, or...
Get Item Files
List all available download formats (PDF, MP4, etc.) and file sizes for a specific...
Get Item Metadata
Get complete details about an item, including its title, subjects, publisher, license, and total view count.
Get Item Reviews
Retrieve community reviews and star ratings to gauge how useful or well-received a specific archived item is.
Get Views Stats
Measure the popularity of an item by getting its total view count and, if available...
Search
Perform broad searches across all media types using complex syntax like AND or...
Wayback Availability
Check if a given URL has been archived and find the closest available snapshot date...
Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on each call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Internet Archive, then connect any of our 5,200+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,200+ others, all in one place
- Add new capabilities to your AI anytime you want
- Connections are secured and governed automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog weekly
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Internet Archive. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS CLOUD
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on each call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
The pain of building research bibliographies is massive.
Today, gathering source material means clicking through specialized sites. You find a potential article, then you have to manually check its date, the author's background, and if it’s public domain before you can even download it. Then you repeat that process for fifty different sources.
With this MCP, your agent handles all those manual checks in one go. You ask for 'all scientific articles about deep sea life from the 1950-1960 period,' and the system uses search_by_collection to find the right pool of content, then searches_by_date_range to narrow it down. You get a list of vetted sources ready to cite.
Getting complete source context with get_item_metadata
Before you copy-paste anything into your report, you usually have to open the item, find the citation box, then maybe click a separate 'details' tab just to see what collection it belongs to. This is tedious and easy to miss.
Now, running get_item_metadata provides everything upfront: the title, subjects, which collections it belongs to, and who published it—all in one shot. You save yourself ten minutes of clicking through dusty web pages.
What Internet Archive MCP does for your AI
This connector gives your agent access to an immense historical data vault. You don't need to learn complex query syntax or navigate endless menus; you just ask for what you want. Whether you’re looking for academic papers from the 1920s, public domain films, or a snapshot of how a website looked ten years ago, your agent finds it automatically.
It pulls data on everything: file formats, subject matter, and community reviews. Because Vinkius hosts this MCP, your client connects once to access this vast resource alongside thousands of other specialized tools.
It’s all about natural conversation. You tell the AI what you need—a dataset from a specific decade, or the original source code for old software—and it handles the deep search and data aggregation process for you.
019d75ba-dd54-717e-a982-2b18480312f5 How to set up Internet Archive MCP
The bottom line is that you get deep access to a global digital library without writing any complex code or navigating multiple websites.
Subscribe to this MCP in Vinkius. No API key is needed; it's a public, free resource.
Start your request using any MCP-compatible client (like Cursor or Claude). Simply ask the agent for historical content by topic, creator, or date range.
The agent executes the search and returns structured data including titles, identifiers, file formats, and direct links to download resources.
Who uses Internet Archive MCP
Historians, journalists, and academic researchers need this. They're tired of spending hours manually cross-referencing decades of data across dozens of different archives just to find a primary source photo or an old article.
Uses the Wayback Machine tool to check how an opposing political group's website looked in 2018, verifying claims by finding archived versions of pages.
Searches for rare books or scientific papers from specific decades using search_by_date_range and get_item_metadata to build a comprehensive bibliography.
Uses the search_by_collection tool to pull public domain films or images for a video essay, ensuring they have clear usage rights information.
Benefits of connecting Internet Archive MCP
You get access to primary source materials. Instead of searching through limited academic databases, the search tool finds everything from old government films (Prelinger Archives) to rare scientific datasets.
Historical verification is instant. The wayback_availability tool lets you check any URL and instantly see if it was archived, telling you exactly when that snapshot occurred.
Data gathering becomes efficient. Use get_item_metadata to pull all the necessary citation info—creator, date, license, subject—before you even plan your download.
You can filter by format with search_by_mediatype. Need a playlist of vintage audiobooks? You limit results only to 'audio' and find them immediately.
It saves research time. Instead of writing complex database queries, the agent handles combining criteria like creator AND date range using the powerful search tool.
Internet Archive MCP use cases
Tracing website evolution for journalism
A journalist needs to prove a company's messaging changed drastically in 2015. They ask their agent to check the URL using wayback_availability, finding multiple snapshots over time and retrieving metadata on content changes.
Building a film history database
A student wants all public domain films from the 1940s. They use search_by_collection with 'prelinger' and then filter by date using search_by_date_range to narrow down the decade.
Identifying original source materials
A developer is looking for old computing software. They use search_by_mediatype set to 'software' and then get_item_metadata on a promising result to check its specific file formats and download links.
Academic literature review
A researcher needs all articles written about climate change in the 1980s. They use search_by_date_range combined with 'pubmed' (a collection) to pinpoint primary academic sources from that specific period.
Internet Archive MCP tradeoffs
What to watch out for, and the recommended way to handle each one.
Searching for general concepts
Asking the agent, 'Tell me about history,' or 'Find something old.' The search results will be useless and overwhelming.
Always use specific tools. Instead of vague terms, combine criteria: Use search_by_collection to pick a source (like 'gutenberg'), then refine with search_by_date_range for the exact decade you need.
Assuming full access to data
Just asking for a file download without checking what formats are available, leading to an error.
Before downloading, use get_item_files on the item ID. This shows you exactly which formats (MP3, EPUB, PDF) and sizes are ready for you.
Ignoring specialized search syntax
Writing a query like 'World War II films' when they need to find only articles about the subject. This leads to mixed media types.
Use specific tools or refine your broad search with field-specific parameters (e.g., title:'WWII' AND mediatype:movies) in the main search tool.
When to use Internet Archive MCP
Use this MCP if your job requires deep, historical data retrieval from non-standardized archives, especially when verifying web content or accessing public domain media spanning decades. If you need to check a website's history, use wayback_availability; if you only need academic papers, stick to search_by_collection with 'pubmed'. Don't use this MCP if your requirement is simple: for example, if you just want today's stock prices or the latest news headlines. For real-time, rapidly changing data, a dedicated API connection (like a live financial feed) will be more appropriate than an archive.
Frequently asked questions about Internet Archive MCP
How do I use Internet Archive MCP if I don't know the exact name? +
You can start with a broad search using the main search tool. You just need to describe the topic, and the agent will help you refine it by date or media type.
Does Internet Archive MCP handle modern websites? +
It uses the wayback_availability tool for this. If a site was online before, it checks its historical snapshots; otherwise, it won't find an archived version.
Can I search for films and books at the same time using Internet Archive MCP? +
Yes. You can use the main search tool to combine criteria, like searching for 'climate change' AND limiting it by mediatype:movies or mediatype:texts.
What is the best way to check a file's availability? +
Use get_item_files. This tool gives you a precise list of all available formats (PDF, EPUB, etc.) and their corresponding download links for that specific item ID.
Is Internet Archive MCP only for American content? +
No, it covers global content. You can use search_by_collection to browse international libraries or use the main search tool with country-specific keywords.