mcp-kindle
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-kindlelist my recent Kindle books"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-kindle
mcp-kindle is a read-only, source-scoped MCP server for local Kindle library data.
Version 0.1.0 reads from the local Kindle database or XML export cache. It is intended for direct LLM read access without exposing any write path, and follows the shared conventions documented in mcp-source-playbook and mcp-source-foundation.
Implemented
MCP stdio server via
mcp-kindle-serverprofile and health reporting
library reads through
kindle_libraryfocused unit tests for XML parsing and profile behavior
Related MCP server: rekordbox-mcp
Tools
kindle_profilekindle_healthkindle_library
Configuration
At least one local source must be available:
export KINDLE_DB_PATH="/path/to/kindle.db"
export KINDLE_XML_PATH="/path/to/KindleSyncMetadataCache.xml"CLI
mcp-kindle profile --format json
mcp-kindle library --format json
mcp-kindle-serverSafety
read-only by default
local-file based, with no cloud mutation path in v1
no credentials are required unless a future cloud connector is added
Development
python -m pytestThis server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/kogecoo/mcp-kindle'
If you have feedback or need assistance with the MCP directory API, please join our Discord server