TalkToAnki

Provides MCP endpoints to manage Anki decks, notes, syncing, and study analytics via AnkiConnect.

python

GitHub Stars

python

Language

5 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": {
    "muxuuu-talktoanki": {
      "command": "python",
      "args": [
        "/path/to/your/project/TalkToAnki/talktoanki_server.py"
      ],
      "env": {
        "LOG_LEVEL": "INFO",
        "MAX_RETRIES": "3",
        "REQUEST_TIMEOUT": "30.0",
        "ANKI_CONNECT_URL": "http://localhost:8765",
        "CONNECTION_TIMEOUT": "10.0",
        "ANKI_CONNECT_VERSION": "6"
      }
    }
  }
}

TalkToAnki is an MCP server that unifies Anki with your AI assistant, enabling powerful deck and note management through AnkiConnect. You can query decks and notes, create and update content, sync data, and analyze study progress from an MCP client. This makes it easy to automate study workflows, build tutoring tools, or integrate Anki-powered capabilities into your AI agents.

How to use

You interact with TalkToAnki through an MCP client by invoking the available endpoints to manage decks, notes, and study data. Start the server locally, then point your MCP client to the local process. Use the server to search for notes, create or update cards, sync Anki, and retrieve study statistics. All actions are exposed as MCP endpoints, so you can compose requests in your MCP client to achieve tasks like creating a new deck, adding notes in bulk, or querying due cards for your study sessions.

How to install

Prerequisites you need before installing are Python 3.8 or newer, the desktop version of Anki with the AnkiConnect plugin installed, and an MCP client that can talk to the server (for example Cursor or another MCP-capable client). Ensure Anki is running before starting the MCP server.

Step-by-step commands to set up and run the server on your machine are below. Follow each line exactly.

Clone the project, install dependencies, and run the server. Use your actual paths where indicated.

Additional sections

Configuration and environment you can tune to control how TalkToAnki connects to AnkiConnect and logs information.

Configuration details

The server relies on AnkiConnect to communicate with Anki. You configure connection details and logging through environment variables. The primary URL for AnkiConnect defaults to http://localhost:8765, and the server can be run with standard Python tooling.

Troubleshooting

If you encounter connection issues, verify that Anki is running and that AnkiConnect is installed and enabled. Check firewall rules to ensure port 8765 is reachable, and restart both Anki and the MCP client if needed. Review logs for any errors related to connectivity or timeouts.

Examples and usage notes

You can perform common tasks such as creating a deck, adding notes, finding notes, syncing the database, and retrieving study progress. Build your MCP requests to call these actions in sequence as part of larger automation flows.

Available tools

anki_get_server_info

Retrieves server status and current configuration information.

anki_get_deck_names

Fetches a list of all card decks (卡组) in the Anki collection.

anki_create_deck

Creates a new deck (card group) in Anki.

anki_get_deck_stats

Returns statistics for a specific deck, such as card counts and study activity.

anki_add_note

Adds a new note to a deck, creating a new card based on the selected note type.

anki_find_notes

Searches for notes matching a query and returns matching note IDs.

anki_get_note_info

Fetches detailed information about a specific note.

anki_sync

Synchronizes the local Anki collection with the connected Anki instance.

anki_update_note

Updates the content or tags of an existing note.

anki_delete_notes

Deletes multiple notes in a single operation.

anki_move_notes

Moves notes to another deck.

anki_suspend_notes

Suspends or resumes learning for selected notes.

anki_batch_add_notes

Adds multiple notes in a single request.

anki_batch_update_tags

Updates tags for a batch of notes.

anki_export_deck

Exports a deck to an .apkg file.

anki_change_note_type

Changes the note type (template) for selected notes.

anki_get_note_types

Retrieves available note types and their fields.

get_due_cards

Retrieves cards that are due for review in a given deck.

get_study_progress

Provides detailed study progress statistics for a deck.

get_review_history

Returns review history and success analysis.

Built by

VeilStrat

AI signals for GTM teams