Skip to main content
Glama
Calibre RAG MCP Server

Calibre RAG MCP Server

by ispyridis

Calibre RAG MCP Server

Enhanced Calibre MCP server with RAG (Retrieval-Augmented Generation) capabilities for project-based vector search and contextual conversations.

Features

  • RAG-Enhanced Search: Vector-based semantic search using FAISS and Transformers

  • Project-Based Organization: Create isolated vector search projects for different contexts

  • Multi-Format Support: Process books in various formats (EPUB, PDF, MOBI, etc.)

  • OCR Capabilities: Extract text from images and scanned PDFs using Tesseract

  • Advanced Text Processing: Natural language processing for better content understanding

  • Windows Compatible: Designed specifically for Windows environments

Related MCP server: Personal Research Assistant MCP

Technologies Used

  • Vector Search: FAISS for efficient similarity search

  • Embeddings: Xenova Transformers for local embedding generation

  • OCR: Tesseract for optical character recognition

  • PDF Processing: Multiple PDF parsing libraries (pdf-parse, pdf-poppler, pdf2pic)

  • Image Processing: Sharp for image manipulation

  • NLP: Natural language processing with multiple libraries

Prerequisites

  • Node.js >= 16.0.0

  • Calibre installed on Windows

  • ImageMagick (for enhanced image processing)

  • Tesseract OCR (for text extraction from images)

Installation

  1. Clone this repository:

git clone https://github.com/yourusername/calibre-rag-mcp-nodejs.git
cd calibre-rag-mcp-nodejs
  1. Install dependencies:

npm install
  1. Run setup (Windows):

setup.bat

Configuration

The server automatically detects your Calibre library location. For custom configurations, modify the settings in server.js.

Usage

Starting the Server

npm start

Available Tools

  • search: Semantic search across your ebook library

  • fetch: Retrieve specific content from books

  • list_projects: List all RAG projects

  • create_project: Create a new RAG project

  • add_books_to_project: Add books to a project for vectorization

  • search_project_context: Search within specific projects

Example MCP Configuration

Add to your MCP client configuration:

{
  "mcpServers": {
    "calibre-rag": {
      "command": "node",
      "args": ["path/to/calibre-rag-mcp-nodejs/server.js"]
    }
  }
}

Project Structure

calibre-rag-mcp-nodejs/
├── server.js              # Main MCP server
├── package.json           # Dependencies and scripts
├── setup.bat              # Windows setup script
├── test-*.js              # Various test files
├── projects/              # RAG projects storage
├── CONFIG.md              # Configuration documentation
├── USAGE_EXAMPLES.md      # Usage examples
└── QUICK_TEST.md          # Quick testing guide

Testing

Run the test suite:

npm test

Individual test files:

  • test-enhanced-server.js - Enhanced server functionality

  • test-ocr-full.js - OCR capabilities

  • test-pdf-approaches.js - PDF processing

  • test-enhanced-auto.js - Automated testing

Documentation

Requirements

System Requirements

  • Windows 10/11

  • Node.js 16+

  • Calibre installed

  • At least 4GB RAM (8GB+ recommended for large libraries)

Optional Dependencies

  • ImageMagick (for enhanced image processing)

  • Tesseract OCR (for text extraction from scanned documents)

Troubleshooting

Common Issues

  1. FAISS Installation: If FAISS fails to install, ensure you have proper build tools

  2. Tesseract Not Found: Install Tesseract and add to PATH

  3. Memory Issues: Reduce batch sizes for large document processing

Debug Mode

Enable verbose logging by setting environment variable:

set DEBUG=calibre-rag:*
npm start

Contributing

  1. Fork the repository

  2. Create a feature branch

  3. Make your changes

  4. Add tests for new functionality

  5. Submit a pull request

License

Licensed under the Apache License 2.0. See LICENSE file for details.

Support

For issues and questions, please open an issue on GitHub.

Changelog

v1.0.0

  • Initial release with RAG capabilities

  • Project-based vector search

  • Multi-format document support

  • OCR integration

  • Windows optimization

Available Tools

7 tools
add_books_to_projectC

Add books to a RAG project for vectorization and context search

Inputs: project_name (required), book_ids (required).

create_projectB

Create a new RAG project for vector-based book search

Inputs: name (required), description.

fetchC

Fetch specific content from a book using epub:// URL

Inputs: url (required).

get_project_infoB

Get detailed information about a specific RAG project

Inputs: project_name (required).

list_projectsB

List all available RAG projects

Inputs: no named parameters.

search_project_contextC

Search for relevant context chunks within a RAG project using vector similarity

Inputs: project_name (required), query (required), limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 7 tools

    Disambiguation4/5

    Most tools have distinct purposes, with clear boundaries between project management (create_project, list_projects, get_project_info, add_books_to_project, search_project_context), book content access (fetch), and general library search (search). The only potential overlap is between 'search' and 'search_project_context', but their descriptions clarify that one searches the library while the other searches within a specific project's vectorized context.

    Naming Consistency5/5

    All tools follow a consistent snake_case verb_noun pattern with clear, descriptive names. The naming convention is uniform throughout: create_project, list_projects, get_project_info, add_books_to_project, search_project_context, fetch, and search. No deviations or mixed styles are present.

    Tool Count5/5

    With 7 tools, the count is well-scoped for the server's purpose of managing Calibre RAG projects and searching ebook content. Each tool appears to earn its place, covering project lifecycle operations, content retrieval, and search functionality without being overly sparse or bloated.

    Completeness4/5

    The tool set provides good coverage for RAG project management (create, list, get info, add books, search context) and book access/search (fetch, search). A minor gap is the lack of project deletion or update tools, which could limit full lifecycle management, but core workflows for creating, populating, and querying projects are well-supported.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides AI agents with research capabilities for local Calibre e-book libraries, including fulltext search across titles, ISBNs, and comments, plus structured excerpt retrieval from books.
      2
      GPL 3.0
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables semantic search and conversational querying across a personal research library of PDFs, DOCX, and other documents using a vector database. It provides tools for document summarization, finding related papers, and high-accuracy retrieval for AI clients like Claude Desktop.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables searching, reading, and managing a Calibre ebook library through natural language, with features like metadata search, full-text search, content extraction, and library management.
      Apache 2.0