mcp-calibre
by jumpifequal
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CALIBRE_LIBRARY | No | Path to the Calibre library. Auto-detected from %APPDATA%\calibre\global.py.json, then ~\Calibre Library. | |
| CALIBRE_MCP_DATA | No | Directory for the server's sidecar index/data files. Default: %LOCALAPPDATA%\calibre-mcp. | |
| CALIBRE_LIBRARIES | No | Several libraries, semicolon-separated on Windows (colon elsewhere); the first is the default. | |
| CALIBRE_MCP_STEMMING | No | Set to 1 to build a second, Porter-stemmed FTS5 index. Default: 0. | |
| FASTEMBED_CACHE_PATH | No | Directory where the embedding model is cached. Default: %LOCALAPPDATA%\calibre-mcp\models. | |
| CALIBRE_EBOOK_CONVERT | No | Path to Calibre's ebook-convert executable. Auto-detected from PATH, then Calibre2\ebook-convert.exe under Program Files. | |
| CALIBRE_MCP_LOG_LEVEL | No | Log level (INFO or DEBUG). Default: INFO (DEBUG also logs queries). | |
| CALIBRE_MCP_MAX_CHARS | No | Cap per read call (controls token usage). Default: 12000. | |
| CALIBRE_MCP_HTTP_TOKEN | No | Bearer token required for --transport http (min 24 chars). Generate with --gen-token. | |
| CALIBRE_MCP_EMBED_MODEL | No | Sentence-embedding model name. Default: sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2. | |
| CALIBRE_MCP_THROTTLE_MS | No | Pause in milliseconds per indexed document. Default: 5. | |
| CALIBRE_MCP_EMBED_BACKEND | No | Embedding backend: fastembed (default) or hash (lexical fallback for tests/air-gapped machines). | |
| CALIBRE_MCP_EMBED_THREADS | No | Number of threads used for embedding. Default: half the CPU cores. | |
| CALIBRE_MCP_SYNC_INTERVAL | No | Background index sync interval in seconds (0 = startup only). Default: 600. | |
| CALIBRE_MCP_CONVERT_TIMEOUT | No | Timeout in seconds per ebook-convert conversion. Default: 180. | |
| CALIBRE_MCP_EMBED_MAX_CHUNKS | No | Maximum chunks embedded per book. Default: 300. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo issues