Wayback Machine
Integrates the Internet Archive Wayback Machine's functionalities, enabling users to list website snapshots and retrieve archived web pages through a Model Context Protocol server.
About
This Model Context Protocol (MCP) server provides seamless access to the vast archives of the Internet Archive Wayback Machine. Inspired by the TypeScript server described in the LobeHub listing, it allows users to programmatically interact with historical web data. Whether you need to track website changes over time, retrieve specific archived versions of pages, or perform advanced searches across archive.org items, this tool simplifies the process by exposing these capabilities through a standardized protocol, making it ideal for developers and data enthusiasts.
Key Features
- Fetch the content of specific archived web pages by URL and timestamp, including the option for original content.
- List website snapshots using the Wayback CDX API, with filters for URL, date range, limit, and match type.
- Directly access archived page content via a custom `wayback://{url}/{timestamp}` resource URI.
- 0 GitHub stars
- Search for items across archive.org collections by query, media type, creator, and various other fields.
Use Cases
- Build applications that need to display or process content from archived web pages.
- Programmatically retrieve historical versions of websites for research or analysis.
- Automate the search and retrieval of digital items within the Internet Archive for data collection.
