MCP

Converse with Your Digital Library

AI-powered eBook server for EPUB/PDF. Interact naturally with your digital library, extract content, and get metadata.


90
Spark score
out of 100
Updated 4 months ago
Version 1.0.0

Add to Favorites

Why it matters

Unlock the knowledge within your EPUB and PDF library. This MCP server enables natural language conversations, allowing you to query, summarize, and interact with book content like never before.

Outcomes

What it gets done

01

Extract metadata and table of contents from EPUB and PDF files.

02

Enable conversational querying of book content using natural language.

03

Generate summaries and answer questions based on book material.

04

Support interactive learning through content-based quizzes and exercises.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-ebook-mcp | bash

Capabilities

Tools your agent gets

get_all_epub_files

Retrieve all EPUB files in a specified directory

get_metadata

Extract metadata from EPUB files (title, author, publication date, etc.)

get_toc

Retrieve table of contents from EPUB files

get_chapter_markdown

Get chapter content in Markdown format from EPUB files

get_all_pdf_files

Retrieve all PDF files in a specified directory

get_pdf_metadata

Extract metadata from PDF files

get_pdf_toc

Retrieve table of contents from PDF files

get_pdf_page_text

Get text content from specific PDF pages

+2 tools

Overview

eBook MCP Server

What it does

This MCP server processes EPUB and PDF eBooks, enabling AI-driven interaction with your digital library. It supports extracting metadata (title, author, dates), table of contents, and chapter content in Markdown format. It also allows for retrieving PDF metadata, table of contents, and specific page text or Markdown content.

How it connects

Use this tool when you need to build an AI-powered interface for interacting with a collection of EPUB and PDF documents. It's ideal for creating conversational experiences around books, enabling content navigation via natural language, and supporting active learning through generated quizzes or exercises.

Source README

A powerful Model Context Protocol server for processing eBooks (EPUB and PDF) that enables natural conversation with your digital library through AI-powered interaction.

Installation

From Source

git clone https://github.com/yourusername/ebook-mcp.git
cd ebook-mcp
uv pip install -e .

Configuration

Cursor

"ebook-mcp":{
    "command": "uv",
    "args": [
        "--directory",
        "/Users/onebird/github/ebook-mcp/src/ebook_mcp/",
        "run",
        "main.py"
    ]
}

Available Tools

Tool Description
get_all_epub_files Retrieve all EPUB files in a specified directory
get_metadata Extract metadata from EPUB files (title, author, publication date, etc.)
get_toc Retrieve table of contents from EPUB files
get_chapter_markdown Get chapter content in Markdown format from EPUB files
get_all_pdf_files Retrieve all PDF files in a specified directory
get_pdf_metadata Extract metadata from PDF files
get_pdf_toc Retrieve table of contents from PDF files
get_pdf_page_text Get text content from specific PDF pages
get_pdf_page_markdown Get content in Markdown format from specific PDF pages
get_pdf_chapter_content Retrieve chapter content and corresponding page numbers by chapter title

Features

  • Smart library management - search books by format or topic
  • Interactive reading experience - have conversations about book content
  • Active learning support - create quizzes and exercises based on books
  • Content navigation - find sections using natural language queries
  • Support for EPUB and PDF formats
  • Metadata extraction (title, author, dates)
  • Table of contents extraction
  • Chapter content extraction with Markdown output
  • Batch processing capabilities

Usage Examples

Show me all EPUB files in my downloads folder
Find books about GenAI in my library
Give me a brief introduction to 'LLM Engineer Handbook'
What's covered in Chapter 3?
Summarize the key points about RAG from this book

Resources

Notes

PDF processing relies on document structure - some functions may not work if table of contents is unavailable. For large PDF files, it's recommended to process by page ranges. EPUB chapter IDs should be obtained from the table of contents structure. Available in multiple languages: English, Chinese, Japanese, Korean, French, and German.

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.