Daizo (Buddhist Text Corpora)

Provides access to Buddhist text corpora including CBETA Chinese texts, SAT Daizōkyō database, and Pali Tipitaka with fuzzy search across titles, content-based regex search with context extraction, and intelligent text parsing that handles TEI markup and encoding for scholarly research and comparative textual analysis.

Buddhist text retrieval MCP server by Shinryo Taniguchi that provides AI assistants with access to two major Buddhist text corpora: CBETA (Chinese Buddhist Electronic Text Association) TEI XML files and SAT (SAT Daizōkyō Text Database) web content, plus Pali Tipitaka texts from VipassanaTech. Built in Rust with automatic data cloning from GitHub repositories, the implementation offers fuzzy search across titles with Unicode normalization for Chinese characters and Pali diacritics, content-based regex search with line number context extraction, and intelligent text extraction that handles TEI markup, juan sections, and encoding detection. The server includes SAT web scraping with title scoring algorithms, supports both LSP-style and newline-delimited JSON framing modes, and provides structured metadata including bibliographic information, section headings, and content statistics, making it valuable for Buddhist studies research, comparative textual analysis, and scholarly work requiring access to primary sources across multiple Buddhist traditions and languages.