Mousetail

Provides an interface to manage Anki collections via an MCP client, including create/read/update/delete operations and optional sync with AnkiWeb or self-hosted servers.

python

5

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "listfold-mousetail": {
      "command": "uv",
      "args": [
        "run",
        "python",
        "-m",
        "mousetail.mcp.stdio_server"
      ],
      "env": {
        "PYTHONUNBUFFERED": "1"
      }
    }
  }
}

Mousetail is an MCP server that connects Anki to an LLM by directly using Anki’s pylib API. It requires no addons and focuses on core deck and note operations, making it a simple, stable bridge between your Anki collections and conversational AI workflows.

How to use

You interact with Mousetail through a client that speaks the MCP protocol. Start the server with a single command and then issue tools to manage your Anki collections from your preferred LLM or automation setup. Core capabilities include creating, reading, updating, and deleting notes and decks, syncing your collection across devices, and optional media synchronization.

How to install

Prerequisites you need to have before running Mousetail are an active Anki installation and a supported runtime to host the MCP server. You should also have Python installed on your system as part of the development and runtime workflow.

Install and set up the MCP runtime tool, then run Mousetail using the standard startup command.

Configuration and usage notes

Sync your Anki collection with AnkiWeb or a self-hosted sync server to keep your decks in sync across devices. You can store credentials securely using the system credential store and choose between AnkiWeb, self-hosted servers, or collection-only sync. The server automatically discovers available Anki collections and can be configured to use a default sync endpoint if you provide one.

Key configuration points you may adjust include the sync endpoint and whether media should be synced. If conflicts occur during syncing, perform a sync from Anki Desktop first to resolve them. All credentials are stored securely and never in plain text.

Build/run flow and development notes

A typical development setup uses a local MCP server exposed via stdio. The development configuration demonstrates starting the MCP server with an MCP runner and a stdio-based server bridge. Restart tooling when you change the configuration to ensure the server is reloaded.

Available tools

list_collections

Discover available Anki collections on this system, enabling subsequent operations without additional path configuration.

create_deck

Create a new Anki deck based on your conversation with the LLM.

create_note

Create a new note in the current collection from content provided by the LLM.

read_note

Retrieve a note by ID or query to review or validate content.

update_note

Update an existing note with new content or metadata.

delete_note

Remove a note from the collection.

sync_collection

Sync the local Anki collection with AnkiWeb or a self-hosted server, with options for media sync and collection-only sync.