Anki MCP Server

List all available Anki decks.

Get all notes/cards from a specific deck.

Get a random sample of notes from a specific deck to understand typical note structure.

Get the note types (models) and their field definitions used in a specific deck.

Create a new note in the specified deck with the given fields and tags.

Update specific fields of an existing note. Perfect for adding audio or other content to existing cards.

Create a new deck and optionally a new note type with specified fields and card templates.

List all available note types (models) with their fields and card templates.

Generate audio file from text using Google Cloud Chirp TTS API and return base64 encoded audio data.

Create multiple notes in a single batch operation for efficiency. Handles duplicates gracefully by reporting which notes are duplicates while still creating non-duplicate notes.

IMPORTANT: The auto_audio parameter must be passed as a dictionary/object structure with fields: enabled, source_field, target_field, language, and voice. Do NOT pass it as a JSON string. Set to null (or omit) to disable automatic audio generation.

Example auto_audio object:
{
    "enabled": true,
    "source_field": "Hanzi",
    "target_field": "Audio",
    "language": "cmn-cn",
    "voice": "cmn-CN-Chirp3-HD-Achernar"
}

Save base64 encoded media data as a file in Anki's media collection for use in cards.

Generate audio from text and save it to Anki's media collection, returning filename for use in cards.

Update multiple notes in a single batch operation for efficiency. Each update should contain note_id and fields to update.

Find notes that contain the search text as a substring in any field. Simple and reliable text matching.