mcpField
M
mcp-anki-server

mcp-anki-server

Local
github.com/cdpathScience & Education1Updated 67w ago
Repository

About mcp-anki-server

mcp-anki-server connects MCP clients to Anki Desktop through Anki Connect. It requires Anki Desktop, Anki Connect, and uv; the README provides setup instructions for Cursor and Chatwise.

Key features

  1. 01Connect to Anki Desktop through Anki Connect
  2. 02Run with uvx
  3. 03Setup instructions for Cursor and Chatwise

Use cases

  1. 01Connect Cursor to an Anki installation
  2. 02Add Anki tools in Chatwise

MCP support

Provides an MCP server for connecting to Anki Desktop using Anki Connect. The README describes configuration for Cursor and Chatwise.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "anki": {
      "command": "uvx",
      "args": [
        "mcp-server-anki"
      ]
    }
  }
}
Run commanduvx mcp-server-anki

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypimcp-server-anki

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

mcp-anki-server

for go version, see https://github.com/cdpath/anki-mcp

prerequisite

usage

cursor

update .mcp.json to add the following:

{
    "mcpServers": {
      "anki": {
        "command": "uvx",
        "args": ["mcp-server-anki"],
        "env": {},
        "disabled": false,
        "autoApprove": []
      }
    }
}
chatwise

Go to Settings -> Tools -> Add and use the following config:

Type: stdio
ID: Anki
Command: uvx mcp-server-anki

local development

uv --directory $HOME/Developer/mcp-server-anki/src/mcp_server_anki run server.py

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.