AIBase
EN
Explore
Anki MCP Server
A

Anki MCP Server

A server based on the Model Context Protocol (MCP) that enables AI assistants to interact with the Anki spaced - repetition flashcard application, supporting the creation, management, and review of cards through natural language.
Education and learning toolsKnowledge management and memory#Anki integration#Flashcard learning#AI assistant#Learning tool.TypeScript
2.5 points
3.2K
Open Site

Overview

Installation

Content Details

Alternatives

What is Anki MCP Server?

Anki MCP Server is a bridge tool that connects the Anki flashcard learning software with AI assistants (such as Claude and ChatGPT). It allows you to manage your learning content by having conversations with the AI assistant in natural language: create flashcards, review knowledge points, manage learning plans, etc. Imagine this: You are learning Spanish and can directly tell the AI assistant, 'Help me create 10 Spanish flashcards about restaurant conversations.' The AI will automatically generate them and add them to Anki. Or you can ask, 'Which cards need to be reviewed today?' The AI will tell you and guide you through the review process.

How to use Anki MCP Server?

Using Anki MCP Server is very simple, mainly in two modes: 1. **Local mode**: Install it on your computer and use it with desktop AI assistants such as Claude Desktop. 2. **Remote mode**: Access your Anki through web - based AI assistants (such as ChatGPT and Claude.ai). Regardless of the mode, the core process is: Install the software → Configure the connection → Start learning by having conversations with the AI.

Applicable scenarios

Anki MCP Server is particularly suitable for the following learning scenarios: • **Language learning**: Let the AI help you generate vocabulary cards and conversation practice cards. • **Exam preparation**: Quickly create knowledge point cards and intelligently arrange review plans. • **Skill learning**: Organize knowledge in professional fields such as programming, medicine, and law. • **Daily learning**: Convert reading notes and meeting points into reviewable flashcards. • **Teaching assistance**: Teachers can create learning materials in batches for students.

Main features

Intelligent review and learning
The AI assistant can obtain the cards that need to be reviewed, show them to you, and record your mastery level. It optimizes the learning plan according to Anki's spaced repetition algorithm.
Deck management
Create, view, and manage different learning decks, and organize your learning content by topic or subject.
Note/card management
Create, search, update, and delete learning cards. It supports rich query syntax and can accurately find the content you need.
Multimedia support
Add multimedia content such as pictures and audio to the cards. The AI can automatically obtain media files from file paths or network URLs and add them to the cards.
Template management
View and manage the styles and fields of card templates to ensure that the card display meets your requirements.
One - click remote access
Use the --ngrok parameter to create a secure remote access tunnel, allowing web - based AI assistants to access your local Anki.
Multi - client support
Supports multiple AI clients, including Claude Desktop, Cursor IDE, Cline, Zed Editor, etc.
Advantages
Natural language interaction: Manage your learning through conversations without memorizing complex operations.
Intelligent content generation: The AI can automatically generate learning card content according to your needs.
Multi - platform support: Supports both desktop AI assistants and web - based AI tools.
Improved learning efficiency: Combines the creativity of AI with Anki's scientific review algorithm.
Easy to install: Provides a one - click installation package to simplify the configuration process.
Open - source and free: Based on the AGPL open - source license, it can be freely used and modified.
Limitations
Requires Anki and AnkiConnect: You must first install the Anki software and its plugin.
Network dependency: The remote mode requires a stable network connection.
Learning curve: Initial configuration may require some technical knowledge.
Beta stage: The functions are still being improved and may be unstable.
Security considerations: You need to pay attention to protecting the access link during remote access.

How to use

Install Anki and AnkiConnect
First, make sure that the Anki software is installed on your computer, and install the AnkiConnect plugin in Anki. AnkiConnect is an API plugin for Anki that allows other programs to interact with Anki.
Select the installation mode
Choose the installation method according to your usage scenario: • Use Claude Desktop: Download the.mcpb file for one - click installation. • Use other desktop AI clients: Install via npm. • Use web - based AI: Run in HTTP mode and create an ngrok tunnel.
Configure the connection
Ensure that AnkiConnect is running normally (default address: http://localhost:8765). If you need remote access, use the --ngrok parameter to create a secure tunnel.
Start learning conversations
Open your AI assistant and start managing your Anki learning content in natural language. For example: 'Help me create 10 French vocabulary cards' or 'Show the cards that need to be reviewed today.'

Usage examples

Language learning assistant
You are learning Spanish and want the AI to help you create practice cards for daily conversations.
Exam review plan
You have a programming exam in a week and need to quickly create review cards for key knowledge points.
Daily learning management
You want to know what learning tasks you need to complete today.
Content search and organization
You want to find all cards about a specific topic for concentrated review.

Frequently Asked Questions

Do I need to pay to use Anki MCP Server?
Is this tool safe? Will it leak my learning data?
Which AI assistants are supported?
Can I use it on my phone or tablet?
What should I do if I encounter problems during installation?
Will this tool affect the normal use of Anki?
Can I expand the functions myself?
Why does the card update sometimes fail?

Related resources

Official documentation website
Complete tutorials, examples, and usage guides.
GitHub repository
Source code, issue feedback, and contribution guidelines.
Anki official website
Download the Anki flashcard learning software and access the official documentation.
AnkiConnect plugin
An API plugin for Anki, a necessary component.
Model Context Protocol
Official documentation and specifications of the MCP protocol.
Claude Desktop
Download the desktop version of the Claude AI assistant.
npm package page
Information and version history of the npm installation package.

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "anki-mcp": {
      "command": "npx",
      "args": ["-y", "@ankimcp/anki-mcp-server", "--stdio"],
      "env": {
        "ANKI_CONNECT_URL": "http://localhost:8765"
      }
    }
  }
}

{
  "mcpServers": {
    "anki-mcp": {
      "command": "ankimcp",
      "args": ["--stdio"],
      "env": {
        "ANKI_CONNECT_URL": "http://localhost:8765"
      }
    }
  }
}

{
  "mcpServers": {
    "anki-mcp": {
      "command": "node",
      "args": ["/path/to/anki-mcp-server/dist/main-stdio.js"],
      "env": {
        "ANKI_CONNECT_URL": "http://localhost:8765"
      }
    }
  }
}

{
  "mcpServers": {
    "stdio-server-debug": {
      "type": "stdio",
      "command": "node",
      "args": ["--inspect-brk=9229", "dist/main-stdio.js"],
      "env": {
        "MCP_SERVER_NAME": "anki-mcp-stdio-debug",
        "MCP_SERVER_VERSION": "1.0.0",
        "LOG_LEVEL": "debug"
      },
      "note": "Anki MCP server with debugging enabled on port 9229"
    }
  }
}

{
  "mcpServers": {
    "anki-mcp": {
      "command": "node",
      "args": [
        "--inspect=9229",
        "<path_to_project>/anki-mcp-server/dist/main-stdio.js"
      ],
      "env": {
        "ANKI_CONNECT_URL": "http://localhost:8765"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

C
Cipher
Cipher is an open-source memory layer framework designed for programming AI agents. It integrates with various IDEs and AI coding assistants through the MCP protocol, providing core functions such as automatic memory generation, team memory sharing, and dual-system memory management.
TypeScript
0
5 points
S
Shadcn Ui MCP Server
An MCP server that provides shadcn/ui component integration for AI workflows, supporting React, Svelte, and Vue frameworks. It includes functions for accessing component source code, examples, and metadata.
TypeScript
11.8K
5 points
A
Annas MCP
The MCP server and CLI tool of Anna's Archive are used to search for and download documents on the platform and support access through an API key.
Go
6.7K
4.5 points
A
Apple Notes MCP
A server that provides local Apple Notes database access for the Claude desktop client, supporting reading and searching of note content.
Python
12.2K
4.3 points
M
MCP Server Weread
The WeRead MCP Server is a lightweight service that bridges WeRead data and AI clients, enabling in - depth interaction between reading notes and AI.
TypeScript
12.0K
4 points
M
MCP Obsidian
This project is an MCP server used to interact with the Obsidian note application through the Local REST API plugin of Obsidian. It provides various tools to operate and manage files in Obsidian, including listing files, retrieving file content, searching, modifying content, and deleting files.
Python
14.9K
5 points
M
MCP Atlassian
MCP Atlassian is a Model Context Protocol server designed for Atlassian products (Confluence and Jira), supporting both cloud and on-premises deployments and providing AI assistant integration functions.
Python
14.0K
5 points
M
MCP Youtube
Download YouTube subtitles via yt - dlp and connect to Claude.ai through the MCP protocol for video content analysis
TypeScript
11.8K
4 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
18.0K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
28.0K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
17.4K
4.5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
52.7K
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
51.1K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
22.3K
5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
18.1K
4.5 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
35.6K
4.8 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2025AIBase