anki-mcp-addon
Provides tools for interacting with an Anki collection, allowing management of notes, decks, cards, study sessions, and insights.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@anki-mcp-addonShow me my due cards for today."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
anki-mcp-addon
Talk to your Anki collection. Point Claude (or any MCP client) at your flashcards and study, edit, and analyze your deck in plain conversation. No AnkiConnect, no Node.js, no external dependencies. It's a small Python add-on that runs an MCP server inside Anki itself.
Why
Anki is powerful but manual: browsing, tagging, and reviewing all happen through the desktop UI. This add-on turns your collection into something an LLM can actually work with, so you can ask for things instead of clicking through them:
"Quiz me on today's due cards, one at a time."
"Turn these notes into 15 flashcards and put them in my Spanish deck."
"How's my retention been this month? Which decks am I falling behind on?"
"Find every card tagged
hard, move them into a Review deck.""I got that one wrong, mark it Again."
Everything runs locally. Your collection never leaves your machine except through whatever MCP client you're already using.
Related MCP server: Anki MCP Server
Prerequisites
Anki 23.10 or later (Python 3.9+ bundled)
An MCP-compatible client (Claude Code, Claude Desktop, Cursor, Zed, etc.)
Installation
Via AnkiWeb (recommended)
Anki → Tools → Add-ons → Get Add-ons
Paste this code:
593632040Restart Anki
Manual (for development or the latest unreleased code)
Find your Anki add-ons directory: Anki → Tools → Add-ons → View Files (opens
%APPDATA%\Anki2\addons21\on Windows)Copy (or symlink) this repo's root folder (the one containing
__init__.pyandmanifest.json) into that add-ons directoryRestart Anki
Either way, the MCP server starts automatically when you open a profile. It listens on http://127.0.0.1:8766.
Optional: change port
Tools → Add-ons → anki-mcp → Config opens a settings dialog. Change the port and click "Save and restart"; no need to restart Anki.
Client setup
Claude Code
claude mcp add anki --transport sse http://127.0.0.1:8766/sseRestart Claude Code. Anki must be open whenever you use it.
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"anki": {
"url": "http://127.0.0.1:8766/sse"
}
}
}Other MCP-compatible clients
Use SSE transport URL: http://127.0.0.1:8766/sse
Refer to each client's MCP documentation for where to configure SSE servers.
Available tools
Notes
Tool | Description |
| Create Basic or Cloze notes. Supports batch. |
| Search with Anki browser syntax. Returns up to |
| Edit note fields in place by note ID. Preserves scheduling data. |
| Tag notes by ID. Supports |
| Delete notes by ID (also deletes associated cards). |
| Move notes to another deck. |
Decks
Tool | Description |
| Create deck or subdeck ( |
| List all decks with due/new/learn counts. |
| Delete decks by name. |
Study
Tool | Description |
| Get cards due for review (default limit 20, max 100). |
| Record answer for a card: 1=Again, 2=Hard, 3=Good, 4=Easy. |
| Postpone cards by N days. |
| Suspend or unsuspend cards. |
| Reset cards to new state. Preserves note content and tags. |
Insights & sync
Tool | Description |
| Retention stats, overdue count, mature/young cards for a deck or all decks. |
| Trigger AnkiWeb sync. |
Development
pip install pytest
pytestTests run without Anki. The aqt and anki modules are mocked via tests/conftest.py.
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/luiz-santos-it/anki-mcp-addon'
If you have feedback or need assistance with the MCP directory API, please join our Discord server