Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
MCP server for Calibre ebook library access
CalibreMCP connects a Calibre library to MCP-capable assistants so they can search books, inspect metadata, export text, and manage library tasks. It uses FastMCP, reads Calibre's `metadata.db`, and adds semantic search with LanceDB plus full-text retrieval for book content. The repo also includes a Calibre plugin, a webapp, and packaging files for Windows installs.
Builders who want their agent to work with a Calibre ebook library from Cursor or another MCP client.
You can ask your agent to find, inspect, and organize books in Calibre instead of doing every step by hand.
What it does
FastMCP server
Runs a Calibre library service over MCP with stdio and HTTP support.
Library search and management
Exposes tools for searching books, reading metadata, updating records, and handling shelves.
Semantic and full-text retrieval
Indexes library metadata in LanceDB and supports full-text chunk search for RAG-style queries.
Calibre GUI plugin
Includes a plugin that extends Calibre with AI-assisted workflows inside the desktop app.
Companion webapp
Ships a Next.js dashboard for chat, semantic search, skills, and import workflows.
Windows packaging
Includes desktop build and install files for a Windows-native setup.
How to get it
- 1Developers from source
git clone https://github.com/sandraschi/calibre-mcp cd calibre-mcp just sync just start-webapp
- 2Run
# Development install git clone https://github.com/sandraschi/calibre-mcp.git cd calibre-mcp uv sync # Or via MCPB package npx mcpb install calibre-mcp
README
CalibreMCP
📖 Installation Guide — download the
.exefrom Releases, double-click, done
FastMCP 3.2 MCP server for Calibre e-book library management — AI-assisted search, RAG, and agentic workflows for Sandra's 1000+ book library.
Quick Start
Download Calibre MCP_*_x64-setup.exe from Releases → double-click → launch Calibre MCP. Install guide.
Developers from source:
git clone https://github.com/sandraschi/calibre-mcp
cd calibre-mcp
just sync
just start-webapp
// claude_desktop_config.json { "mcpServers": { "calibre-mcp": { "command": "uv", "args": ["run", "calibre-mcp"], "env": { "CALIBRE_LIBRARY_PATH": "L:/Multimedia Files/Written Word/Calibre-Bibliothek" } } } } Then ask Claude: "Find unread sci-fi books", "Open a random Banks novel", or "What's my library health?"
What is this?
calibre-mcp 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 21 portmanteau tools for natural-language library management.
Read more
| Topic | Description |
|---|---|
| About Calibre | What Calibre is, how it stores data, access methods |
| About Calibre Web | calibre-web vs Calibre Content Server, running both together |
| About Plugins | CalibreMCP Integration plugin, calibreops-bridge, roadmap |
| About MCP Tools | 21 portmanteau tools, architecture, agentic flows |
| About AI Workflows | RAG, FTS, skills, prompts, sampling, agentic chaining |
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/sandraschi/calibre-mcp.git
cd calibre-mcp
uv sync
# Or via MCPB package
npx mcpb install calibre-mcp
Features
- FastMCP 3.2 — Universal connect (stdio + HTTP), sampling, agentic tool chaining
- 21 portmanteau tools — Consolidated operations (search, manage, export, OCR, viewer)
- 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.
Files in the repo
- .claude-plugin
- .github
- .opencode
- .snapshots
- assets
- calibre_plugin
- calibre-plugins
- config
- cua-reports
- docs
- hooks
- lancedb_test_calibre
- mcpb
- moltbot-skill
- native
- prompts
- samples
- scratch
- scripts
- skills
- src
- src-tauri
- tests
- tools
- webapp
- .assess-fix-timestamp
- .cursorrules
- .dockerignore
- .env
- .env.example
- .gitattributes
- .gitignore
- .mcpbignore
- .pre-commit-config.yaml
- .windsurfrules
- AGENTS.md
- BUILD_LOG.md
- build.ps1
- calibre_mcp_integration.zip
- calibre-mcp-backend.spec
- Cargo.lock
- Cargo.toml
- CHANGELOG.md
- CLAUDE.md
- config.json
- CONTRIBUTING.md
- curl_out.json
- debug_mcp_tools.py
- extension.toml
- extension.wasm
- fleet-start.config.ps1
- glama.json
- INSTALL.md
- justfile
- LICENSE
- llms-full.txt
- llms.txt
- manifest.json
- package-lock.json
- pyproject.toml
- QUERY_BOOKS_FIX_IMPLEMENTATION.md
- README.md
- repro_arxiv.py
- requirements-dev.txt
- restart.bat
- SECURITY.md
- server.json
- setup.py
- start.bat
- start.ps1
- stop.bat
- test_out_new.txt
- test_out.txt
- test_out3.txt
- test_out4.txt
- test_out5.txt
- test_out6.txt
- TODO.md
- uv.lock
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
20 MB lightweight cross-platform database client for 90+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | 轻量级跨平台数据库管理工具,支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、达梦等 90+ 数据库,提供桌面端、Docker、CLI、内置 AI 助手和 MCP Server。