Anki MCP Server

Anki MCP Server

A Model Context Protocol server that bridges Claude AI with Anki flashcard app, allowing users to create and manage flashcards using natural language commands.

Category
访问服务器

README

anki-mcp-server

smithery badge

Read this in other languages: English, 한국어

A Model Context Protocol (MCP) server that connects Claude and Anki, allowing you to easily create flashcards using natural language.

Introduction

anki-mcp-server acts as a bridge between Claude and the Anki app, enabling communication between them. This allows you to give natural language commands to Claude to create and manage Anki flashcards. For example, if you request "Add an easy Japanese vocabulary card to my Japanese deck," Claude will automatically create an appropriate card.

Requirements

  • Python 3.8 or higher
  • Anki 2.1.x or higher
  • AnkiConnect add-on
  • Claude Desktop (or an environment with access to Claude API)

Installation

1. Setting up Anki and AnkiConnect

  1. Install Anki.
  2. Install the AnkiConnect add-on:
    • Run Anki and select Tools > Add-ons > Get Add-ons from the top menu
    • Enter the code 2055492159 and click 'OK'
    • Restart Anki

2. Installing anki-mcp-server

# Clone the repository
git clone https://github.com/dhkim0124/anki-mcp-server.git
cd anki-mcp-server

# Create and activate a virtual environment (optional)
python -m venv venv
source venv/bin/activate  # Windows: venv\Scripts\activate

# Install required packages
pip install -r requirements.txt

Configuration

Claude Desktop Setup

Modify the Claude Desktop configuration file to register the MCP server:

  1. Claude Desktop configuration file location:

    • Windows: %APPDATA%\Claude\claude_desktop_config.json
    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Linux: ~/.config/Claude/claude_desktop_config.json
  2. Add the following content to the configuration file:

{
  "mcpServers": {
    "anki-mcp": {
      "command": "python",
      "args": ["path/anki_server.py"],
      "env": {}
    }
  }
}

Replace path/anki_server.py with the absolute path to your anki_server.py file.

How to Use

  1. Run the Anki application and keep it running in the background.
  2. Launch Claude Desktop.
  3. You can give Claude natural language commands such as:

Example Commands

  • "Add an easy Japanese vocabulary card to my Japanese deck"
  • "Create a card for the English word 'perseverance' with its meaning and example sentences"
  • "Summarize the programming concepts I learned today into a card"
  • "Create 5 history timeline cards"

Claude will interpret these requests and create appropriate cards in Anki through the MCP server.

Key Features

Card Creation Features

  • Basic question-answer format card creation
  • Language learning card creation (word, meaning, example sentences)
  • Automatic tag addition
  • Adding cards to multiple decks

Deck Management Features

  • View available deck list
  • Create new decks
  • Search for cards in specific decks

Troubleshooting

Connection Issues

  • Check if Anki is running: The MCP server requires Anki to be running to communicate with it.
  • Verify AnkiConnect: Make sure AnkiConnect is properly installed. Visit http://localhost:8765 in your web browser to confirm you see the "AnkiConnect v.6" message.
  • Firewall settings: Windows users may need to allow firewall access for Anki.

MCP Server Issues

  • Check logs: If problems occur, check the server logs for error messages.
  • Restart: If issues persist, try restarting Anki, Claude Desktop, and the MCP server.

Extension and Contribution

If you'd like to contribute to the project, fork the GitHub repository and submit a pull request. We welcome contributions in the following areas:

  • Support for new card types
  • Improved language support
  • Interface improvements
  • Documentation improvements

License

This project is distributed under the MIT License. See the LICENSE file for details.

Contact

For issues or questions, please contact us through GitHub issues.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选