This project provides an MCP server for processing eBooks, specifically EPUB and PDF formats, enabling natural language interaction with digital content. It targets users and developers seeking to integrate LLM capabilities with their digital libraries, offering benefits like smart content retrieval, interactive learning, and simplified navigation.

How It Works

Ebook-MCP acts as a Model Context Protocol (MCP) server, facilitating communication between LLM applications and e-book processing tools. It utilizes libraries such as ebooklib for EPUBs and PyPDF2/PyMuPDF for PDFs to extract metadata, tables of contents, and chapter content. This architecture allows for intuitive, conversation-based querying and interaction with digital books, enhancing user engagement and knowledge extraction.

Quick Start & Requirements

• Installation: Clone the repository and install dependencies using uv: uv pip install -e ..
• Running: Development mode: uv run mcp dev src/ebook_mcp/main.py. Production mode: uv run src/ebook_mcp/main.py.
• Prerequisites: Python, uv.
• Integration: Configuration examples for Cursor IDE are provided.

Highlighted Details

• Comprehensive support for EPUB and PDF formats, including metadata extraction, TOC retrieval, and chapter content retrieval (with Markdown output).
• Enables advanced use cases such as smart library management, interactive Q&A, active learning support, and natural language content navigation.
• Designed for seamless integration with AI-powered IDEs like Cursor.
• Batch processing capabilities for both EPUB and PDF files.

Maintenance & Community

No specific details regarding maintainers, community channels (e.g., Discord, Slack), or roadmap are present in the provided README snippet.

Licensing & Compatibility

The license type and compatibility for commercial use are not explicitly stated in the provided README snippet.

Limitations & Caveats

PDF processing is dependent on the availability of a document's table of contents; functionality may be degraded without it. For large PDF files, processing by page ranges is recommended to manage memory usage. EPUB chapter identification relies on parsing the table of contents structure.