MokuPDF

[](https://www.python.org/downloads/) [](https://badge.fury.io/py/mokupdf) [](https://opensource.org/licenses/MIT) [](https://modelcontextprotocol.io/)

MokuPDF is a powerful, MCP (Model Context Protocol) compatible server that enables AI applications to read and process PDF files with advanced capabilities. It combines intelligent file search, comprehensive text extraction, image processing, and optional OCR support to handle any type of PDF document - from simple text files to complex scanned documents.

> 🚀 Perfect for Claude Desktop, ChatGPT plugins, and any AI application that needs PDF processing capabilities!

• ✨ Key Features
• 📦 Installation
• 🎯 Quick Start
• 🔧 MCP Configuration
• 📚 Available Tools
• 💡 Usage Examples
• 🖼️ Image & Scanned PDF Support
• 🔍 Smart File Search
• ⚙️ Configuration Options
• 🛠️ Development
• 🤝 Contributing
• 📄 License

• 📄 Full Text Extraction - Extract all text content from any PDF
• 🖼️ Advanced Image Handling - Extract embedded images as base64 PNG with proper format conversion
• 📱 Scanned PDF Support - Auto-detects and renders image-based/scanned PDFs at high resolution
• 🔤 Optional OCR Integration - Extract text from scanned documents using Tesseract (optional)
• 📑 Page-by-Page Processing - Handle large PDFs efficiently without memory issues