Clanki 2.0: Your AI's Supercharged Bridge to Anki! MCP Server

@jrherediaramirez

Repository

Basic information

About Clanki 2.0: Your AI's Supercharged Bridge to Anki! MCP Server

MCP server enabling AI assistants (like Claude) to control Anki via AnkiConnect

#ai #mcp #anki #claude #anki-connect

Clanki 2.0: Your AI's Supercharged Bridge to Anki! MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "Clanki-2.0": {
      "command": "npx",
      "args": [
        "@modelcontextprotocol/inspector",
        "node",
        "build/index.js"
      ]
    }
  }
}

Clanki 2.0: Your AI's Supercharged Bridge to Anki! MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Clanki 2.0?

Clanki 2.0 is a Model Context Protocol (MCP) server that gives AI assistants, like Claude, direct and intelligent access to your Anki desktop flashcard collection. It integrates with Anki via the AnkiConnect plugin and is designed for learners who want to automate or enhance their study workflow through an AI.

How to use Clanki 2.0?

Ensure Anki is running with AnkiConnect installed, and Node.js 18+ is available. Clone the repository, run npm install and npm run build. Then add the server to your MCP client’s configuration (e.g., claude_desktop_config.json) with "command": "node" and "args": ["/absolute/path/to/clanki/build/index.js"]. Start your AI assistant to begin using the tools.

Key features of Clanki 2.0

Create, delete, and get statistics for Anki decks
Create basic and cloze‑deletion cards, including batch creation
Update existing cards and delete notes by Note ID
Retrieve detailed card information (status, interval, reviews, etc.)
Suspend or unsuspend cards by Card ID or Anki query
Search cards using flexible criteria or raw Anki query syntax

Use cases of Clanki 2.0

Automatically creating flashcards from AI‑generated study materials
Organizing and cleaning up decks by deleting obsolete decks or notes
Suspending difficult cards during a study session without manual clicks
Gathering deck statistics for progress tracking and review planning
Batch‑creating hundreds of cards from a structured data source

Frequently asked questions

What prerequisites are needed?

Anki desktop must be running with the AnkiConnect plugin installed. Node.js version 18 or higher is required.

How do I configure Clanki 2.0 with my AI assistant?

Edit your MCP client’s configuration file (e.g., `claude_desktop_config.json`) and add a `"clanki"` entry with `"command": "node"` and `"args": ["/absolute/path/to/clanki/build/index.js"]`. Replace the path with the absolute location of your build folder.

Can I delete whole decks using Clanki 2.0?

Yes, the `delete-deck` tool permanently removes an entire deck and all its cards. This action is irreversible, so use it with caution.

How do I search for specific cards?

Use the `query-cards` tool, which accepts many optional filters (deck, tags, card state, text content, added

Comments

More Developer Tools MCP servers

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

endoflife.ai

Free MCP server for software end-of-life intelligence: EOL dates, support status, and the 0-100 EOL Risk Score across 480+ tracked products. Agents can check a single version, pull a product's full lifecycle schedule, or

Routebase

Routebase keeps your API's design, docs, contract tests, mocks and monitoring in one living OpenAPI spec so they can't drift apart. Agents work on that same source of truth, under your team's permissions.

SSH MCP Server

hypnosis

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.