Anki MCP Server Integration

What does “Anki” MCP Server do?

The Anki MCP (Model Context Protocol) Server bridges the Anki desktop application with AI assistants by leveraging the Anki-Connect add-on. This server enables seamless access to Anki’s flashcard database, allowing AI models to interact programmatically with your decks. Tasks such as retrieving cards due for review, accessing unseen or new cards, and even creating new flashcards can be executed directly through the MCP interface. Developers and users can thus enhance their study workflows by integrating LLMs for smart review, automatic flashcard creation, and more, all built on top of Anki’s robust spaced repetition system. This integration is particularly valuable for educational, productivity, and memory-augmentation tools seeking to automate or enrich flashcard-based learning.

List of Prompts

No prompt templates are listed or described in the repository.

List of Resources

• anki://search/deckcurrent
  • Returns all cards from the current deck. Equivalent of deck:current in Anki.
• anki://search/isdue
  • Returns cards in review and learning waiting to be studied. Equivalent of is:due in Anki.
• anki://search/isnew
  • Returns all unseen cards. Equivalent of is:new in Anki.

List of Tools

• update_cards
  • Marks cards with given card IDs as answered and assigns them an ease score (1 = Again, 4 = Easy).
  • Inputs: Array of objects with cardId (number) and ease (number).
• add_card
  • Creates a new card in the Default Anki deck.
  • Inputs: front (string), back (string).
• get_due_cards
  • Returns a specified number of cards currently due for review.
  • Input: num (number).
• get_new_cards
  • Returns a specified number of new cards.
  • Input: num (number).

Use Cases of this MCP Server

• Automated Card Review
  • Integrate with an AI assistant to automatically fetch and review cards that are due, streamlining study sessions.
• Intelligent Flashcard Creation
  • Use LLMs to generate new flashcards on-demand based on user notes or external content, adding them directly to Anki.
• Progress Monitoring
  • Retrieve the state of new, seen, and due cards to help users visualize and manage their learning progress.
• Adaptive Learning
  • Adjust card scheduling or recommend reviews based on user performance, leveraging AI insights with Anki’s scheduling.
• Seamless Study Workflows
  • Connect Anki review tasks with other productivity or study tools to create an integrated learning environment.

How to set it up

Windsurf

1. Ensure you have Node.js installed and the Anki-Connect add-on enabled in your Anki desktop.
2. Install the Anki MCP Server:
   npm install @anki/mcp-server@latest
3. Edit your Windsurf configuration file to add the MCP server:

   {
     "mcpServers": {
       "anki-mcp-server": {
         "command": "/path/to/anki-mcp-server/build/index.js"
       }
     }
   }
   

4. Save the config and restart Windsurf.
5. Verify the server is running by checking for Anki MCP integration in your AI assistant.

Claude

1. Ensure Node.js is installed and Anki-Connect is running in Anki.
2. Install Anki MCP Server.
3. Locate and edit the Claude Desktop config file:
   On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
   On Windows: %APPDATA%/Claude/claude_desktop_config.json
4. Add the following configuration:

   {
     "mcpServers": {
       "anki-mcp-server": {
         "command": "/path/to/anki-mcp-server/build/index.js"
       }
     }
   }
   

5. Save and restart Claude. Check that Anki MCP Server is accessible.

Cursor

1. Install Node.js and ensure Anki-Connect is enabled.
2. Install Anki MCP Server.
3. Edit the Cursor configuration to include:

   {
     "mcpServers": {
       "anki-mcp-server": {
         "command": "/path/to/anki-mcp-server/build/index.js"
       }
     }
   }
   

4. Save and restart Cursor to enable the server.

Cline

1. Set up Node.js and Anki-Connect.
2. Install Anki MCP Server.
3. Update your Cline config:

   {
     "mcpServers": {
       "anki-mcp-server": {
         "command": "/path/to/anki-mcp-server/build/index.js"
       }
     }
   }
   

4. Save the file and restart Cline to activate the server.

Securing API Keys

If you need to provide secrets or API keys, use environment variables. Example:

{
  "mcpServers": {
    "anki-mcp-server": {
      "command": "/path/to/anki-mcp-server/build/index.js",
      "env": {
        "ANKI_CONNECT_API_KEY": "${ANKI_CONNECT_API_KEY}"
      },
      "inputs": {
        "apiKey": "${ANKI_CONNECT_API_KEY}"
      }
    }
  }
}

Note: Replace ANKI_CONNECT_API_KEY with your actual environment variable.

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "anki-mcp-server": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “anki-mcp-server” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the available information, the Anki MCP Server offers solid integration for flashcard automation and review. The lack of prompt templates and sampling features limits its flexibility, but its toolset is robust for its intended purpose. The documentation is clear, and setup instructions are available. Overall, this MCP scores a 7/10 for utility and clarity, especially for Anki users.

MCP Score