The Internet Archive is a non-profit digital library offering free universal access to books, movies & music, as well as 624 billion archived web pages.
An MCP-native research assistant — search backend, intent-routing, and writing pipeline that carries a question through search, verification, and writing, delivering whatever research you need: quick answers, verified sources, or a finished document.
4
7
157 npm
MIT
Why this server?
Provides tool for retrieving historical URLs archived under a domain via the Wayback Machine.
Enables AI-driven open-source intelligence investigations by exposing 30 tools for scanning emails, usernames, domains, IPs, and more, with real subprocess execution.
31
55 PyPI
9
MIT
Why this server?
Search scanned datasheets and databooks from the Internet Archive.
Aggregates 17 free, keyless research sources into a single MCP server, enabling unified search for papers, code, models, trends, standards, and electronic components with deduplicated results.
8
MIT
Why this server?
Provides tools for searching inside digitised books, browsing the catalogue, reading item records, and accessing Wayback Machine snapshots.
An MCP server for the Internet Archive that enables searching the full text of digitized books, browsing the catalogue, and reading Wayback Machine captures. No API key or configuration required.
6
135 npm
1
MIT
Why this server?
Allows checking the history and content of websites via the Internet Archive's Wayback Machine, providing access to archived snapshots to verify how long a page or domain has existed.
Aggregates search results from multiple providers (web, academic, code, finance) with a unified JSON schema, providing both an HTTP API and an MCP server for AI agent tooling.
14
60
MIT
Why this server?
Provides tools to interact with the Internet Archive's Wayback Machine, including archiving URLs, retrieving archived pages as clean text, listing snapshots, searching items, and comparing snapshots.
Provides tools to archive URLs, retrieve clean readable text from Wayback Machine snapshots, list snapshots, search Internet Archive items, and compare snapshots, designed to avoid context window blowup by returning stripped text.
6
8 npm
MIT
Why this server?
Provides access to historical URLs from the Internet Archive for passive reconnaissance.
A scope-aware bug-bounty & reconnaissance MCP server that works out of the box on the Python standard library and augments itself with your favourite CLI tools when they're present.
22
MIT
Why this server?
Allows submitting URLs to the Internet Archive through IndexNow so new or updated pages can be picked up for archiving.
Bing Webmaster Tools and IndexNow for AI agents: traffic, indexing, crawl issues, inbound links, keywords. Direct writes are off by default; changes go through a plan a person applies.