A
securityA
licenseA
qualityA server implementation that connects to a locally running Anki, enabling card review and creation through the Model Context Protocol.
Last updated -
4
168
MIT License
Enables interaction with Anki flashcard software through the AnkiConnect API, allowing creation of decks, adding notes, listing decks and models, searching notes, and retrieving detailed information about note models and their fields.
Serves as the runtime environment for the MCP server, with the README specifying Node.js version 14 or later as a prerequisite.
Anki MCP Server
A Model Context Protocol (MCP) server that enables LLMs to interact with Anki flashcard software through the AnkiConnect API.
Features
Create new decks in Anki
Add notes to existing decks
List available decks and note models
Search for notes using Anki's search syntax
Get detailed information about note models and their fields
Bulk add multiple notes at once
Prerequisites
Node.js (v14 or later)
Anki with the AnkiConnect add-on installed
A Model Context Protocol compatible client (such as Claude with Anthropic MCP support)
Installation
Make sure you have Anki installed with the AnkiConnect add-on
Install AnkiConnect by going to Tools > Add-ons > Get Add-ons and entering code:
2055492159
Clone this repository:
git clone https://github.com/yourusername/anki-mcp-server.git cd anki-mcp-serverInstall dependencies:
npm installBuild the project:
npm run build
Usage
Make sure Anki is running on your computer with AnkiConnect enabled
Start the MCP server:
npm startConnect your MCP client (e.g., Claude) to this server
Available Tools
The server provides the following tools to MCP clients:
listDecks: Get a list of all decks in Anki
listModels: Get a list of all note models/types in Anki
createDeck: Create a new deck in Anki
getModel: Get details about a specific note model/type
addNote: Add a single note to a deck
addNotes: Add multiple notes at once
searchNotes: Search for notes using Anki's search syntax
Examples
Create a New Deck
{
"name": "createDeck",
"arguments": {
"name": "My New Deck"
}
}
Add a Note
{
"name": "addNote",
"arguments": {
"deckName": "My New Deck",
"modelName": "Basic",
"fields": {
"Front": "What is the capital of France?",
"Back": "Paris"
},
"tags": ["geography", "europe"]
}
}
Search Notes
{
"name": "searchNotes",
"arguments": {
"query": "deck:\"My New Deck\" tag:geography"
}
}
Configuration
The server configuration is in the config object in src/index.ts. You can modify:
ankiConnectUrl: URL for the AnkiConnect API (default:http://localhost:8765)apiVersion: API version for AnkiConnect (default:6)defaultDeckName: Default deck to use if none specified (default:Default)
Troubleshooting
Cannot connect to Anki
Make sure Anki is running
Check that AnkiConnect add-on is installed and working
Verify that the AnkiConnect URL is correct (default: http://localhost:8765)
Permission issues with AnkiConnect
AnkiConnect may prompt for permission when the server tries to add cards. Look for a popup in Anki.
License
MIT License
This server cannot be installed
local-only server
The server can only run on the client's local machine because it depends on local resources.
A Model Context Protocol server that allows LLMs to interact with Anki flashcard software, enabling functions like creating decks, adding notes, searching cards, and managing flashcard content through natural language.
Related MCP Servers
- AsecurityFlicenseAqualityA Model Context Protocol server that enables LLMs to interact with Anki flashcard software through AnkiConnect, allowing for creation and management of flashcards, decks, and note types.Last updated -1,024144
- -securityAlicense-qualityA Model Context Protocol server that bridges Claude AI with Anki flashcard app, allowing users to create and manage flashcards using natural language commands.Last updated -4MIT License
- -securityAlicense-qualityA Model Context Protocol server that enables language models to interact with Anki flashcard decks programmatically, with specialized features for Japanese language learning including vocabulary import, sample sentence generation, and spaced repetition review.Last updated -3MIT License