Ebook MCP

🚀 E-book Content Processing Platform (ebook-MCP)

A tool platform for processing and analyzing e-book files, supporting EPUB and PDF formats. It provides functions such as extracting metadata, obtaining table of contents, reading chapter content, and converting content to Markdown format. Additionally, it offers a server-side framework that can be run via commands.

🚀 Quick Start

✨ Features

This platform offers comprehensive functions for both EPUB and PDF file processing:

EPUB Processing Features

1. Retrieve all EPUB files in a specified directory.
2. Extract metadata information (e.g., title, author, publication date) from EPUB files.
3. Read the table of contents structure of EPUB files.
4. Obtain the content of specific chapters and convert it to Markdown format.

PDF Processing Features

1. Retrieve all PDF files in a specified directory.
2. Extract metadata information from PDF files.
3. Read the table of contents structure of PDF files.
4. Obtain the content of specific pages (supporting plain text and Markdown formats).
5. Get the corresponding content and its page number range based on chapter titles.

📦 Installation

Key Dependencies

• ebooklib: A library for processing EPUB files.
• PyPDF2: A basic PDF processing library.
• PyMuPDF: An advanced PDF processing library.
• beautifulsoup4: An HTML parsing tool.
• html2text: A tool for converting HTML to Markdown format.
• pydantic: A data validation framework.
• fastmcp: An MCP server-side framework.

💻 Usage Examples

Basic Usage

EPUB Processing Example

# Get all EPUB files in a specified directory
epub_files = get_all_epub_files("/path/to/books")

# Extract metadata from a single EPUB file
metadata = get_metadata("/path/to/book.epub")

# Read the table of contents structure of an EPUB file
toc = get_toc("/path/to/book.epub")

# Get the content of a specific chapter (in Markdown format)
chapter_content = get_chapter_markdown("/path/to/book.epub", "chapter_id")

PDF Processing Example

# Get all PDF files in a specified directory
pdf_files = get_all_pdf_files("/path/to/books")

# Extract metadata from a single PDF file
metadata = get_pdf_metadata("/path/to/book.pdf")

# Read the table of contents structure of a PDF file
toc = get_pdf_toc("/path/to/book.pdf")

# Get the content of a specific page (in plain text format)
page_text = get_pdf_page_text("/path/to/book.pdf", 1)

# Get the content of a specific page (in Markdown format)
page_markdown = get_pdf_page_markdown("/path/to/book.pdf", 1)

# Get the corresponding content and its page number range based on a chapter title
chapter_content, page_numbers = get_pdf_chapter_content("/path/to/book.pdf", "Chapter 1")

📚 Documentation

API Reference

EPUB APIs

• get_all_epub_files(path: str) -> List[str]: Retrieve all EPUB file paths in a specified directory.
• get_metadata(epub_path: str) -> Dict[str, Union[str, List[str]]]: Extract metadata information from a specified EPUB file.
• get_toc(epub_path: str) -> List[Tuple[str, str]]: Obtain the table of contents structure of a specified EPUB file, returning chapter titles and their corresponding IDs.
• get_chapter_markdown(epub_path: str, chapter_id: str) -> str: Get the content of a specific chapter based on its ID and convert it to Markdown format.

PDF APIs

• get_all_pdf_files(path: str) -> List[str]: Retrieve all PDF file paths in a specified directory.
• get_pdf_metadata(pdf_path: str) -> Dict[str, Union[str, List[str]]]: Extract metadata information from a specified PDF file.
• get_pdf_toc(pdf_path: str) -> List[Tuple[str, int]]: Obtain the table of contents structure of a specified PDF file, returning chapter titles and their corresponding page positions.
• get_pdf_page_text(pdf_path: str, page_number: int) -> str: Get the corresponding content (in plain text format) based on a specified page number.
• get_pdf_page_markdown(pdf_path: str, page_number: int) -> str: Get the corresponding content (in Markdown format) based on a specified page number.