Summary
Your real Anki collection, driven from the conversation instead of the card editor.
Everything routes through AnkiConnect, so Anki has to be open and every change lands in the collection you actually study from. The Google Cloud text-to-speech step is opt-in: without the key you get everything except generated pronunciation audio.
What it is
A FastMCP server that drives the Anki desktop app through the AnkiConnect add-on, for managing decks, notes and note types.
What you get
- Every deck in your collection (list_decks)
- The notes inside a deck you name (get_deck_notes)
- Note and deck management against the running Anki app, including bulk operations
- Pronunciation audio generated with Google Cloud Text-to-Speech Chirp voices, for cards that need sound
- Semantic similarity search across notes, for finding a card you may already have made
Requirements
Anki running on the same machine with the AnkiConnect add-on installed from Anki's add-on browser, and dependencies installed with uv sync. Audio generation is optional and needs a Google Cloud API key.
Setup effort
One command — uvx anki-mcp