Anki MCP Server
Connects to Anki via AnkiConnect to retrieve leech-tagged flashcards for use in Claude Desktop.
Anki MCP Server
An MCP (Model Context Protocol) server for Claude Desktop that connects to Anki via AnkiConnect and retrieves leech-tagged cards.
Features
- Connects to Anki via AnkiConnect API
- Retrieves cards with "leech" tags
- Adds date-stamped review tags to cards
- Provides comprehensive card data for analysis by Claude
- Can be used with Claude Desktop
Prerequisites
- Anki installed and running
- AnkiConnect add-on installed in Anki
- Node.js and npm
Installation
-
Clone this repository:
git clone https://github.com/yourusername/anki-mcp-server.git cd anki-mcp-server -
Install dependencies:
npm install -
Build the project:
npm run build
Configuration
The server can be configured using environment variables. Copy the provided example file to create your own configuration:
cp .env.example .env
Then edit the .env file to customize your settings:
| Environment Variable | Description | Default Value |
|---|---|---|
ANKI_CONNECT_URL | The URL of the Anki Connect API | http://localhost:8765 |
ANKI_CONNECT_VERSION | The version of the Anki Connect API to use | 6 |
ANKI_MOCK_MODE | Enable mock mode for testing (true/false) | false |
If the environment variables are not set, the server will use the default values.
Finding Your Local IP Address for AnkiConnect
If connecting to localhost doesn't work, you'll need to use your computer's local IP address instead. Configure your .env file with:
ANKI_CONNECT_URL=http://YOUR_LOCAL_IP:8765
To find your local IP address:
- macOS: Open Terminal and run
ifconfigoripconfig getifaddr en0(for WiFi) - Windows: Open Command Prompt and run
ipconfig - Linux: Open Terminal and run
ip addr showorhostname -I
Look for IPv4 addresses like 192.168.x.x or 10.x.x.x in the output.
Test Configuration
For testing, a separate configuration file .env.test is provided:
cp .env.example .env.test
Edit .env.test to set test-specific values:
ANKI_CONNECT_URL=http://localhost:8765
ANKI_CONNECT_VERSION=6
ANKI_MOCK_MODE=true
To run in test mode:
npm run start:test
Usage
- Make sure Anki is running with AnkiConnect installed
- Run the MCP server:
npm start
Configuring Claude Desktop
To use this MCP server with Claude Desktop:
-
Open Claude Desktop
-
Edit the Claude Desktop configuration file located at:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json - Linux:
~/.config/Claude/claude_desktop_config.json
- macOS:
-
Add the following configuration to the
mcpServerssection:
{
"mcpServers": {
"anki": {
"command": "node",
"args": ["path/to/anki-mcp-server/dist/index.js"]
}
}
}
Replace "path/to/anki-mcp-server" with the actual path to where you cloned this repository.
MCP Tool Usage
Once configured, you can use the following tools in Claude:
Example Usage
Could you analyze my Anki leech cards and suggest ways to improve my study?
Claude will use the MCP server to retrieve your leech cards and analyze them.
Available Tools
get_leech_cards
Retrieves cards tagged as leeches from Anki.
Parameters:
detailed(optional, boolean, default: true): Whether to return comprehensive card data or just IDscount(optional, number): Number of random cards to return (defaults to all cards)
tag_reviewed_cards
Adds a date-stamped "reviewed" tag to specified cards. This allows you to track which cards you've reviewed with Claude.
Parameters:
card_ids(required, array of numbers): Array of card IDs to tag as reviewedcustom_tag_prefix(optional, string, default: "見直し"): Custom prefix for the tag
The tag will be in the format 見直し::YYYYMMDD (or your custom prefix if specified).
Example usage in Claude:
I've reviewed these cards, please tag them as reviewed: [1234567890, 1234567891]
Troubleshooting
- "Could not connect to Anki" - Make sure Anki is running and AnkiConnect is properly installed
- "No leech cards found" - You don't have any cards tagged as "leech" in Anki
- Connection issues with localhost - If you're unable to connect using
localhost:- Find your local IP address as described in the Configuration section
- Update your
.envfile to useANKI_CONNECT_URL=http://YOUR_LOCAL_IP:8765 - Make sure AnkiConnect is configured to allow connections from your IP address
- Restart the MCP server after making these changes
- Tag not appearing - Make sure you're providing valid card IDs to the
tag_reviewed_cardstool
Testing Mode
For testing without affecting actual Anki data, you can use the mock mode:
- Set
ANKI_MOCK_MODE=truein your.envfile or use the provided.env.testfile - Run the server with
npm run start:test
In mock mode, the server will simulate all Anki operations without actually connecting to Anki. This is useful for testing Claude integrations without risking data changes.
Development
To run the server in development mode with hot reloading:
npm run dev
For development with mock mode enabled:
npm run dev:test
License
MIT
Server Terkait
Bitly MCP Server
Turn your AI assistant into a digital marketing hub that creates, organizes, and analyzes links and QR Codes on demand.
Anki MCP Server
Connects to a local Anki instance to review and create flashcards. Requires the Anki desktop app and Anki-Connect add-on.
OpenAI Tools
A wrapper for OpenAI's built-in tools, enabling functionalities like web search and code execution. Requires an OpenAI API key.
n8n
Provides AI assistants with direct access to the n8n automation platform.
Markdown to any text
Convert markdown to any text format you want
Memento Protocol
Persistent memory for AI agents — store what matters, recall by meaning, skip the rest
ActiveCampaign
Built for the next generation of intelligent experiences, ActiveCampaign's remote MCP server makes it easy for AI agents to understand, store, and use customer context across tools, channels, and workflows.
Mcptix
A simple and powerful ticket tracking system with AI assistant integration.
Sheet-Cello
A specialized Google Sheets integration server that allows the LLM to read, write, and manage spreadsheet data in real-time. This server supports cell-level manipulation, bulk range updates, and full worksheet retrieval, enabling the model to perform data analysis, logging, and automated reporting directly within Google Worksheets.If you have functions which take range value then first read the sheet and decide where user is asking to add data and define range by your own.Provides 46 tools for Gsheet
Google Calendar Integration Project
Manage and interact with Google Calendar events using the Google Calendar API.