Document Reader

소개

The Document Reader is a universal server designed for efficiently extracting text from a wide array of document formats. It supports common types such as PDF, Excel (xlsx, xlsm), Word (docx), CSV, Plain Text, JSON, and Markdown. Engineered with a streaming API, it enables memory-efficient processing of even large files. Key capabilities include smart encoding detection, process-wide rate limiting, and Docker support for isolated deployment, making it ideal for integration with MCP-compatible clients like Cursor for enhanced AI interactions with local files.

주요 기능

• Supports multiple document formats: PDF, Excel, CSV, TXT, JSON, Markdown, DOCX
• Streaming API for memory-efficient processing of large files
• Smart encoding detection for UTF-8, Latin-1, CP1252, ISO-8859-1
• Configurable process-wide rate limiting
• Docker support for isolated execution with non-root user and read-only mounts
• 0 GitHub stars

사용 사례

• Extracting text from local documents for AI-driven summarization and analysis
• Programmatic access to document content for data processing workflows
• Reading specific pages from PDFs or rows from CSV/Excel files for quick insights