list_decksLABSCO 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
Build from source — git clone https://github.com/amidvidy/anki-mcp.git
USE CASES
01
Finding out what is already in your collection
List the decks first, so new cards go into the one you meant.
02
Reviewing the cards in a deck before adding more
Read the notes in that deck and see how they are worded.
03
Turning something you just learned into flashcards
Draft the cards in the conversation and write them into the deck you picked.
04
Adding pronunciation audio to a language deck
Generate the audio with Google Cloud voices as part of the card rather than recording it yourself.
05
Checking you have not already made this card
Search the deck's existing notes for something close before adding a duplicate.
14 tools
Listed in project docs. Your client may show a different list.
get_deck_notesget_deck_sampleget_deck_note_typescreate_noteupdate_notecreate_deck_with_note_typelist_note_typesgenerate_audiosave_media_filegenerate_and_save_audiocreate_notes_bulkupdate_notes_bulkfind_similar_notesBEFORE YOU INSTALL
What to know first
Tools you get
14 tools named in the project's documentation.
Requires
- uv
- Python 3.11+
- Anki running with the AnkiConnect add-on
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone this one yourself.
Server setup
TERMINAL
git clone https://github.com/amidvidy/anki-mcp.git
cd anki-mcp
uv syncIn Anki, go to Tools > Add-ons > Get Add-ons, enter code 2055492159 (AnkiConnect) and restart Anki; keep Anki running
MCP Clients
Claude Desktop
<YOUR_PATH_TO_ANKI_MCP> is the path of your clone. GOOGLE_CLOUD_API_KEY is only needed for audio generation; remove the env block if you do not use it.
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"anki-mcp": {
"command": "uv",
"args": [
"--directory",
"<YOUR_PATH_TO_ANKI_MCP>",
"run",
"server.py"
],
"env": {
"GOOGLE_CLOUD_API_KEY": "<YOUR_GOOGLE_CLOUD_API_KEY>"
}
}
}
}
