Calibre MCP Server
Enables searching and reading books from your Calibre ebook library through MCP. Supports title, author, and full-text search across multiple formats with lightweight Windows-optimized implementation.
README
Calibre MCP Server
A lightweight Node.js MCP server for searching and reading books from your Calibre ebook library. Designed specifically for Windows compatibility.
Features
- Library Search: Search your Calibre library by title, author, or content
- Book Reading: Retrieve and read book contents in various formats
- Metadata Access: Get detailed book information and metadata
- Windows Compatible: Optimized for Windows environments
- Zero Dependencies: Lightweight implementation with no external dependencies
Prerequisites
- Node.js >= 16.0.0
- Calibre installed on Windows
Installation
- Clone this repository:
git clone https://github.com/yourusername/calibre-mcp-nodejs.git
cd calibre-mcp-nodejs
- Install dependencies:
npm install
Usage
Starting the Server
npm start
Available Tools
search: Search for books in your Calibre libraryfetch: Retrieve specific content from books using epub:// URLs
Example MCP Configuration
Add to your MCP client configuration:
{
"mcpServers": {
"calibre": {
"command": "node",
"args": ["path/to/calibre-mcp-nodejs/server.js"]
}
}
}
Configuration
The server automatically detects your Calibre library location. The search looks for Calibre in common installation paths:
C:\Program Files\Calibre2\C:\Program Files (x86)\Calibre2\- Custom paths via environment variables
API Reference
Search Books
// Search by title
search({ query: "title:\"The Great Gatsby\"" })
// Search by author
search({ query: "author:\"F. Scott Fitzgerald\"" })
// Full-text search
search({ query: "green light" })
Fetch Book Content
// Fetch specific book content
fetch({ url: "epub://book_id/chapter_1" })
Project Structure
calibre-mcp-nodejs/
├── server.js # Main MCP server
├── package.json # Dependencies and scripts
├── test.js # Test file
├── test.bat # Windows test script
└── README.md # This file
Testing
Run the test:
npm test
Or use the Windows batch file:
test.bat
Troubleshooting
Common Issues
- Calibre Not Found: Ensure Calibre is installed in a standard location
- Library Access: Make sure the Calibre library is accessible and not locked
- Permissions: Run with appropriate permissions to access Calibre files
Debug Mode
Set the DEBUG environment variable for verbose logging:
set DEBUG=calibre:*
npm start
Supported Formats
The server supports all formats that Calibre can handle:
- EPUB
- MOBI
- AZW/AZW3
- TXT
- HTML
- And many more
Performance
This lightweight server is designed for:
- Fast startup times
- Low memory usage
- Quick search responses
- Minimal system impact
Comparison with RAG Version
This is the lightweight version. For advanced features like vector search, semantic similarity, and RAG capabilities, see calibre-rag-mcp-nodejs.
| Feature | Simple Version | RAG Version |
|---|---|---|
| Basic Search | ✅ | ✅ |
| Book Reading | ✅ | ✅ |
| Dependencies | None | Many |
| Memory Usage | Low | High |
| Vector Search | ❌ | ✅ |
| Semantic Search | ❌ | ✅ |
| OCR Support | ❌ | ✅ |
| Project Organization | ❌ | ✅ |
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests for new functionality
- 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
v2.0.0
- Improved Windows compatibility
- Enhanced search functionality
- Better error handling
- Optimized performance
v1.0.0
- Initial release
- Basic search and fetch functionality
- Windows support
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。