Lucene Search

概要

Leveraging Apache Lucene, this server provides robust full-text search, automatic document crawling, and rich metadata extraction, all accessible via a Model Context Protocol (MCP) conversational interface. It empowers AI assistants to index and manage diverse document collections—including PDFs and Microsoft Office files—without requiring users to possess technical knowledge of search engines, transforming complex search operations into simple, natural language interactions.

主な機能

• Real-time directory monitoring for automatic updates to the index
• 0 GitHub stars
• Full Lucene query syntax support with AI-powered synonym expansion
• Automatic document crawling and indexing for PDFs, Office, and OpenOffice documents
• Rich metadata extraction including language detection, author, title, and creation date
• Seamless integration with MCP clients via STDIO transport and flexible YAML configuration

ユースケース

• Empowering AI assistants to perform context-aware searches on local document collections.
• Automating the indexing and management of personal or team document archives.
• Facilitating natural language queries for complex information retrieval from diverse file types.