Ebook-MCP is a powerful MCP server for processing electronic books. Built on the Model Context Protocol, it provides standardized APIs for seamless integration between LLM applications and e-book processing capabilities, currently supporting EPUB and PDF formats. The server exposes endpoints to discover and extract EPUB and PDF metadata, tables of contents, and structural information, as well as content extraction at the chapter or page level, with Markdown output to facilitate ingestion by LLMs. It supports batch processing of EPUB and PDF files and offers a reference API with functions such as get_all_epub_files, get_metadata, get_toc, and get_chapter_markdown, along with corresponding PDF APIs like get_all_pdf_files, get_pdf_metadata, get_pdf_toc, get_pdf_page_text, and get_pdf_chapter_content. Dependencies include ebooklib, PyPDF2, PyMuPDF, beautifulsoup4, html2text, pydantic, and fastmcp. The project describes a three-layer architecture: an Agent Layer for translation and LLM interactions, an MCP Tool Layer for extraction and generation, and a System/Base Layer for IO and parsing. Ebook-MCP aims to enable natural language conversations and interactive reading experiences over personal library content.