Prepare the server locally
Run this once before adding it to Claude Code.
git clone https://github.com/FaceDeer/calibre_full_mcp_server
cd calibre_full_mcp_server
npm installAdd it to Claude Code
Paste the maintainer's config below, then edit any placeholder values.
{
"libraries": {
"default": {
"path": "d:/ebooks/main_library",
"description": "The primary research library containing technical manuals.",
"default": true,
"permissions": {
"read": [
"title",
"authors",
"tags",
"rating",
"comments"
],
"write": [
"tags",
"rating",
"comments"
],
"delete": false,
"convert": true
},
"import": {
"allowed_paths": [
"d:/downloads/ebook_imports"
],
"allow_delete_source": false
},
"export": {
"allowed_paths": [
"d:/ebook_exports"
],
"allow_overwrite_destination": false
},
"worker_timeout": 300
}
},
"port": 8000,
"enable_worker_logging": false,
"expose_resources_via_tools": true,
"log_level": "warning"
}See the calibre_full_mcp_server README for full setup instructions.
Make your agent remember this setup
calibre-mcp's config, env vars, and the gotchas you hit — recalled in every future Claude Code, Cursor, and Codex session.
npx conare@latestFree · one command · indexes the sessions already on disk. Set up in the browser instead →
What it does
- Advanced metadata and full-text content search
- Direct reading of book content into agent context
- On-the-fly ebook format conversion
- Granular per-library permission controls
- Metadata management and library maintenance
Tools 5
search_booksQuery libraries using book metadata or perform full-text content searches.get_metadataView metadata for a specific book.update_metadataUpdate metadata fields for a book.convert_bookConvert an ebook between formats.read_bookRead the text content of a book into the agent's context.Try it
Original README from FaceDeer/calibre_full_mcp_server
Calibre MCP Server
This MCP server bridges the gap between AI agents and your **Calibre** ebook libraries. It enables agents to interact with your collection as a dynamic knowledge base, allowing them to search, manage, and read your digital libraries. Unlike other MCP servers it can also allow an AI agent to update library metadata and contents if a library's permissions are set to allow it.
Key Features
Advanced Search: Query libraries using book metadata or perform full-text content searches.
Metadata Management: View and update metadata (titles, authors, tags, ratings, etc.) for any book.
Library Maintenance: Add new titles to your collection or remove existing ones.
Format Conversion: Leverage Calibre’s powerful conversion engine to switch between ebook formats (e.g., PDF to EPUB) on the fly.
Direct Reading: Search and read the text content of a book directly into the agent's context window for analysis, summarization, or Q&A.
Granular Permissions: Define strict access controls per library, including read-only modes and field-level write restrictions.
Prerequisites
Calibre: Must be installed on the host system. This server utilizes
calibre-debugto execute worker processes.Concurrency Note: Calibre does not support concurrent access to a single library. Do not point an agent to a library currently being used by the Calibre desktop application or other calibre processes to avoid database corruption. Setting a
worker_timeoutcan reduce the risk of this happening accidentally, but don't rely on that to protect your libraries. Be aware of what you're doing.
Configuration
The server is configured via a JSON file. Since JSON does not support comments, use the structure below as a template.
Example Configuration (`config.json`)
JSON
{
"libraries": {
"default": {
"path": "d:/ebooks/main_library",
"description": "The primary research library containing technical manuals.",
"default": true,
"permissions": {
"read": ["title", "authors", "tags", "rating", "comments"],
"write": ["tags", "rating", "comments"],
"delete": false,
"convert": true
},
"import": {
"allowed_paths": ["d:/downloads/ebook_imports"],
"allow_delete_source": false
},
"export": {
"allowed_paths": ["d:/ebook_exports"s],
"allow_overwrite_destination": false
},
"worker_timeout": 300
}
},
"port": 8000,
"enable_worker_logging": false,
"expose_resources_via_tools": true,
"log_level": "warning"
}
Configuration Schema Reference
Each library is identified by a unique text key and can have its own separate configuration values:
| Key | Description |
|---|---|
path |
Absolute path to the Calibre library (where metadata.db resides). |
description |
Free-form context provided to the agent explaining what this library contains or what its purpose is. |
default |
If true, the agent uses this library if no specific library is targeted. If you only configure one library then this is unnecessary. |
permissions.read |
Set to true (all fields exposed), false (for a write-only library, if you need one), or a list of specific fields (e.g., ["title", "authors"]). |
permissions.write |
List of metadata fields the agent is allowed to modify, true for all fields and false for a read-only library. |
permissions.delete |
Boolean. If false, the agent cannot delete books from the library. |