Archives
Provides programmatic access to the Internet Archive's digitized content, enabling full-text search and OCR text retrieval.
概要
archives-mcp functions as a specialized server for the Internet Archive, empowering users to interact with its extensive collection of digitized books and documents. It offers robust capabilities for performing full-text searches across document contents, delivering paginated results complete with contextual text snippets. The tool also facilitates the download of complete OCR text for any document, automatically selecting the most suitable text format (hOCR, DjVu, or plain text) and optimizing performance through local caching. This allows for efficient data access and integration into various applications requiring deep interaction with archival content.
主な機能
- Full-text search across digitized document contents
- Downloads complete OCR text from any document
- Paginated search results with contextual text snippets
- Automatic selection of best available text format (hOCR, DjVu, plain text) and local caching
- Complex query support including AND/OR/NOT operators, exact phrases, and collection filtering
- 0 GitHub stars
ユースケース
- Integrating Internet Archive data access into existing content management systems or research tools
- Building custom applications that search and display content from the Internet Archive
- Programmatically retrieving OCR text for linguistic analysis or data processing
