Gallica

关于

This tool acts as an MCP server, providing programmatic access to Gallica, the digital library of the Bibliothèque nationale de France (BnF). It enables users to perform comprehensive text searches, retrieve document snippets, apply advanced filters, and download complete OCR texts from millions of digitized documents. By converting user inputs into Contextual Query Language (CQL) queries for Gallica's SRU API, it streamlines the process of extracting valuable historical and cultural data for research and analysis.

主要功能

• Download complete OCR text from any document using its ARK identifier, with local caching
• Conduct advanced searches with filters for creators, document types, date ranges, language, and title
• Perform text searches with boolean operators, exact phrase matching, and grouping
• Retrieve text excerpts showing search terms within specific documents, including page numbers
• Converts user inputs into Contextual Query Language (CQL) queries for Gallica's SRU API
• 0 GitHub stars

使用案例

• Developers building applications that integrate with or analyze Gallica's extensive data
• Researchers exploring historical documents and texts within Gallica's digital library
• Data analysts extracting OCR text for large-scale linguistic or historical studies