Pdf Reader

About

Provides a server for extracting text and images from PDF files. It supports extracting standard text, performing OCR on scanned documents, and extracting images as Base64 encoded data. Includes a built-in web debugger to simplify testing and integration of its capabilities. The server is built upon FastMCP.

Key Features

• Uses the MCP protocol for communication
• Extracts text from PDFs page by page
• 16 GitHub stars
• Includes a web debugging interface for testing
• Extracts images from PDF pages as Base64 encoded data
• Performs OCR to recognize text in scanned PDFs

Use Cases

• Converting scanned documents to editable text via OCR
• Extracting images from PDF files for use in other applications
• Automated extraction of text from PDF documents