Anki MCP Server

A Model Context Protocol (MCP) server that enables LLMs to interact with Anki flashcard software through AnkiConnect.

Features

Tools

• list_decks - List all available Anki decks

• create_deck - Create a new Anki deck

• create_note - Create a new note (Basic or Cloze)

• batch_create_notes - Create multiple notes at once

• search_notes - Search for notes using Anki query syntax

• get_note_info - Get detailed information about a note

• update_note - Update an existing note

• delete_note - Delete a note

• list_note_types - List all available note types

• create_note_type - Create a new note type

• get_note_type_info - Get detailed structure of a note type

Resources

• anki://decks/all - Complete list of available decks

• anki://note-types/all - List of all available note types

• anki://note-types/all-with-schemas - Detailed structure information for all note types

• anki://note-types/{modelName} - Detailed structure information for a specific note type

Related MCP server: Anki MCP Server

Prerequisites

1. Anki installed on your system

2. AnkiConnect add-on installed in Anki

Configuration

Usage with Claude Desktop

Add the server to your claude_desktop_config.json:

Configuration for Cline

Add the server to your Cline MCP settings file inside VSCode's settings cline_mcp_settings.json

Development

Setup

1. Install dependencies:

2. Build the server:

3. For development with auto-rebuild:

Testing

Run the test suite:

This executes tests for:

• Server initialization

• AnkiConnect communication

• Note operations (create/read/update/delete)

• Deck management

• Error handling

Debugging

Since MCP servers communicate over stdio, we recommend using the MCP Inspector:

This provides a browser-based interface for:

• Monitoring MCP messages

• Testing tool invocations

• Viewing server logs

• Debugging communication issues

Example Usage

1. Create a new deck:

2. Add a basic card:

3. Add a cloze deletion card:

Contributing

1. Fork the repository

2. Create your feature branch

3. Run tests: npm test

4. Submit a pull request

Credits

Icon courtesy of macOS Icons

License

MIT License - see LICENSE file for details