CalibreMCP
БесплатноНе проверенBridges your Calibre e-book library with AI assistants via the Model Context Protocol, enabling natural-language library management, semantic search, RAG, and a
Описание
Bridges your Calibre e-book library with AI assistants via the Model Context Protocol, enabling natural-language library management, semantic search, RAG, and agentic workflows.
README
FastMCP 2.0 server for comprehensive Calibre e-book library management through Claude Desktop
FastMCP Python Austrian Efficiency
Austrian efficiency for Sandra's 1000+ book digital library. Built with realistic AI-assisted development timelines (days, not weeks).
🚀 Quick Start
Prerequisites
- Python 3.11+ with pip
- Calibre 6.0+ installed and running
- Calibre Content Server enabled on port 8080
Installation
cd d:\dev\repos\calibremcp
pip install -e .
Start Calibre Server
# Option 1: Through Calibre GUI
# Calibre → Connect/share → Start Content Server
# Option 2: Command line
calibre-server --port=8080
Test Connection
python -c "
from calibre_mcp.calibre_api import quick_library_test
import asyncio
print('✅ Working' if asyncio.run(quick_library_test()) else '❌ Failed')
"
Claude Desktop Integration
Add to your claude_desktop_config.json:
{
"mcpServers": {
"calibre-mcp": {
"command": "python",
"args": ["-m", "calibre_mcp.server"],
"env": {
"CALIBRE_SERVER_URL": "http://localhost:8080"
}
}
}
}
Features
Core Features
- Full Library Access - Search, browse, and manage your entire Calibre collection
- Smart Metadata - Automatic metadata enhancement and validation
- Format Conversion - On-the-fly conversion between formats
- Reading Progress - Track reading progress across devices
- Tag Management - Smart tagging and categorization
- Library Statistics - Detailed insights into your collection
AI-Powered Tools
- Book Recommendations - Get personalized book suggestions based on content similarity
- Content Analysis - Extract entities, themes, and sentiment from book content
- Reading Insights - Analyze your reading habits and preferences
- Metadata Enhancement - AI-assisted metadata correction and enrichment
Advanced Series Management
- Series Analysis - Identify and fix issues in book series
- Metadata Validation - Ensure consistency across your library
- Series Merging - Combine duplicate or related series
- Automatic Organization - Keep your series properly ordered and managed
Usage Examples
AI-Powered Recommendations
# Get book recommendations based on a book
recommendations = await get_book_recommendations(book_id="123")
# Get personalized recommendations based on preferences
preferences = {
"favorite_authors": ["Brandon Sanderson", "N.K. Jemisin"],
"favorite_genres": ["Fantasy", "Science Fiction"]
}
personalized_recs = await get_book_recommendations(user_preferences=preferences)
Content Analysis
# Analyze book content
analysis = await analyze_book_content(
book_content="...",
options={
"extract_entities": True,
"analyze_sentiment": True,
"identify_themes": True
}
)
Series Management
# Analyze series in your library
analysis = await analyze_series(
library_path="/path/to/calibre/library",
update_metadata=True
)
# Fix common series metadata issues
fix_results = await fix_series_metadata(
library_path="/path/to/calibre/library",
dry_run=False
)
# Merge two series
merge_results = await merge_series(
library_path="/path/to/calibre/library",
source_series="The Kingkiller Chronicle",
target_series="Kingkiller Chronicle",
dry_run=True
)
Documentation
Full documentation available at docs/.
Testing
# Unit tests
python -m pytest tests/test_api.py -v
# Integration tests
python -m pytest tests/integration_tests.py -v
# MCP Inspector
python -m calibre_mcp.server
# Opens: http://127.0.0.1:6274
🔧 Configuration
Environment Variables
CALIBRE_SERVER_URL=http://localhost:8080
CALIBRE_USERNAME=your_username # If auth enabled
CALIBRE_PASSWORD=your_password # If auth enabled
CALIBRE_TIMEOUT=30
CALIBRE_DEFAULT_LIMIT=50
With Authentication
# Enable Calibre authentication
calibre-server --port=8080 --enable-auth --manage-users
# Add user and set environment
export CALIBRE_USERNAME="sandra"
export CALIBRE_PASSWORD="your_password"
🚨 Troubleshooting
Connection Failed
# Check if Calibre server is running
netstat -an | findstr 8080 # Windows
curl http://localhost:8080 # Test in browser
No Books Found
# Verify library has books
calibredb list --limit=5
# Check library path
calibre-debug --get-library
Authentication Issues
# Test credentials
curl -u username:password http://localhost:8080/ajax/interface-data/init
See Troubleshooting Guide for comprehensive solutions.
🏗 Architecture
calibremcp/
├── src/calibre_mcp/
│ ├── server.py # 4 FastMCP tools
│ ├── calibre_api.py # HTTP API client
│ └── config.py # Configuration management
├── config/
│ ├── settings.yaml # Server configuration
│ └── calibre_config.yaml # Calibre-specific settings
├── tests/
│ ├── test_api.py # Unit tests
│ └── integration_tests.py # Integration tests
└── docs/ # Complete documentation
💯 Success Metrics
Phase 1 Complete ✅
- ✅ 4/4 core MCP tools implemented and tested
- ✅ FastMCP 2.0 compliance with proper structure
- ✅ Comprehensive error handling and diagnostics
- ✅ Austrian efficiency: 45-minute realistic timeline
- ✅ Production-ready for immediate Claude Desktop use
📄 License
MIT License - Austrian efficiency in e-book management.
Built with Austrian efficiency for Sandra's comprehensive e-book workflow.
"Sin temor y sin esperanza" - practical without hype or doom.
Установка CalibreMCP
У этого сервера нет опубликованного пакета — он собирается из исходников. Открой репозиторий и следуй инструкции в README.
▸ github.com/sandraschi/calibremcpFAQ
CalibreMCP MCP бесплатный?
Да, CalibreMCP MCP бесплатный — установка в пару кликов через Unyly без оплаты.
Нужен ли API-ключ для CalibreMCP?
Нет, CalibreMCP работает без API-ключей и переменных окружения.
CalibreMCP — hosted или self-hosted?
Self-hosted: сервер запускается локально на твоей машине командой из раздела установки.
Как установить CalibreMCP в Claude Desktop, Claude Code или Cursor?
Открой CalibreMCP на unyly.org, выбери вкладку своего клиента (Claude Desktop, Claude Code, Cursor) и нажми Install — конфиг сгенерируется автоматически, без правки JSON.
Похожие MCP
Opencode Omniroute Plugin
OpenCode plugin for the OmniRoute AI Gateway. Drives dynamic model discovery, /connect auth flow, and multi-instance OmniRoute providers via the official @openc
автор: GitHub ActionsRoblox Studio
Enables AI coding tools to control Roblox Studio for workspace exploration, instance manipulation, and script management. It provides tools for playtesting, sce
автор: paralovAntigravity Drawio
MCP server that enables AI assistants to create, parse, render, and validate Draw.io diagrams programmatically.
автор: S-SUJAN-SFetch
Web content fetching and conversion for efficient LLM usage.
AWS KB Retrieval
Retrieval from AWS Knowledge Base using Bedrock Agent Runtime.
автор: modelcontextprotocolSpring AI MCP Server
Provides auto-configuration for setting up an MCP server in Spring Boot applications.
llm-analysis-assistant
A very streamlined mcp client that supports calling and monitoring stdio/sse/streamableHttp, and can also view request responses through the /logs page. It also
автор: xuzexin-hzMCP-Agent
A simple, composable framework to build agents using Model Context Protocol by [LastMile AI](https://www.lastmileai.dev)
автор: lastmile-aiSpring AI MCP Client
Provides auto-configuration for MCP client functionality in Spring Boot applications.
mcp.natoma.ai
A Hosted MCP Platform to discover, install, manage and deploy MCP servers by [Natoma Labs](https://www.natoma.ai)
Compare CalibreMCP with
Не уверен что выбрать?
Найди свой стек за 60 секунд
Автор?
Embed-бейдж для README
Похожее
Все в категории ai
