概览
What is Ebook-MCP?
Ebook-MCP is a Model Context Protocol (MCP) server for processing electronic books in EPUB and PDF formats. It provides standardized APIs that enable LLM applications to interact with e-book content through natural language conversations.
How to use Ebook-MCP?
Clone the repository, install dependencies with uv pip install -e ., then start the server using uv run mcp dev src/ebook_mcp/main.py for development or uv run src/ebook_mcp/main.py for production. Configure the MCP client (e.g., Cursor) with the provided JSON snippet.
Key features of Ebook-MCP
- Extract metadata (title, author, dates) from EPUB and PDF.
- Extract table of contents from EPUB and PDF.
- Extract chapter content with Markdown output.
- Batch process multiple EPUB or PDF files.
- Extract PDF content by page number or chapter title.
- Markdown output support for both formats.
Use cases of Ebook-MCP
- Ask "Show me all EPUB files in my downloads folder" for smart library management.
- Have natural conversations like "Summarize the key points about RAG from this book."
- Create quizzes or exercises based on book chapters for active learning.
- Navigate content with queries like "Find all sections discussing prompt engineering."
FAQ from Ebook-MCP
Which ebook formats does Ebook-MCP support?
Currently supports EPUB and PDF formats.
How do I start the Ebook-MCP server in production mode?
Run uv run src/ebook_mcp/main.py from the project directory.
What are the main dependencies of Ebook-MCP?
Key dependencies include ebooklib, PyPDF2, PyMuPDF, beautifulsoup4, html2text, pydantic, and fastmcp.
How do I configure Ebook-MCP with Cursor?
Add the JSON configuration to Cursor with the uv command, pointing to the main.py script in the src/ebook_mcp directory.
Are there any limitations with PDF processing?
PDF processing relies on the document's table of contents; extraction may vary depending on the PDF's structure.
