CalibreMCP

📖 Installation Guide — source installation is available now; packaged desktop and MCPB artifacts will be available after the fork's first release

FastMCP 3.4.2+ MCP server for Calibre e-book library management, AI-assisted search, RAG, and agentic workflows.

Naming

• Repository and Python distribution: calibremcp

• Python import package: calibre_mcp

• Command-line executable: schip-mcp-calibre

• Product name: CalibreMCP

The hyphenated calibre-mcp form remains only where it is an established external identifier, such as the application-data directory.

Related MCP server: access-calibre

Quick Start

The detached fork has not published a release yet. Run it from source:

git clone https://github.com/Jarzembak/calibremcp.git
cd calibremcp
uv sync
uv run schip-mcp-calibre --http
# --http starts the HTTP transport on the configured CalibreMCP port.

claude_desktop_config.json:

{
"mcpServers": {
"calibremcp": {
"command": "uv",
"args": ["run", "--directory", "C:\\path\\to\\calibremcp", "schip-mcp-calibre"],
"env": {
"CALIBRE_LIBRARY_PATH": "C:\\path\\to\\Calibre Library"
}
}
}
}

The --directory argument makes uv run the executable from the cloned CalibreMCP project.

For file-based configuration, copy config.example.json to the ignored local file config.json and replace the placeholder values. Environment variables override values from that file.

Then ask Claude: "Find unread sci-fi books", "Open a random Banks novel", or "What's my library health?"

What is this?

CalibreMCP bridges your Calibre e-book library and AI assistants (Claude Desktop, Cursor, etc.) via the Model Context Protocol. It reads Calibre's metadata.db directly, indexes metadata for semantic search (LanceDB RAG), and exposes portmanteau tools, analysis helpers, and interactive cards for natural-language library management.

Read more

Key links

• Documentation hub — curated entry

• Documentation index — full map of ~100 docs

• Tauri desktop — maintainer build and production pitfalls

• Cookbook — goal-oriented recipes

• API reference — all MCP tools and endpoints

• Configuration — env vars and library setup

• Troubleshooting — common issues and fixes

• Webapp README — Next.js dashboard on ports 10720/10721

• Plugin README — Calibre GUI plugin install and usage

• Plugin repo — calibreops-bridge (RAG/AI plugin)

Installation

# Development install
git clone https://github.com/Jarzembak/calibremcp.git
cd calibremcp
uv sync

# Run the stdio MCP server
uv run schip-mcp-calibre

After the first fork release is published, Claude Desktop bundle installations will use calibremcp-v<version>.mcpb from Releases.

Features

• FastMCP 3.4.2+ — Universal connect (stdio + HTTP), sampling, agentic tool chaining

• Consolidated MCP tools — Search, management, export, RAG, analysis, and viewer operations

• Metadata RAG (LanceDB) — Semantic search over title, authors, tags, comments

• Full-text chunk RAG — FTS-driven book content retrieval

• Calibre FTS — Phrase search with PDF page / EPUB spine locations

• Calibre plugin — Extended metadata editor + VL from query in Calibre GUI

• Webapp — Next.js dashboard with AI chat, Semantic Search, Skills, Smart Import

• Skills & prompts — Reusable agentic workflows (recommendations, library health, etc.)

• Concurrency-safe — Thread-safe DB operations for multi-client access

• Windows-native — Unicode-safe, runs reliably on Windows

Austrian efficiency for digital libraries. Built with realistic AI-assisted development timelines.