Get the FREE Ultimate OpenClaw Setup Guide →

omikuji

MCP server from Sunwood-ai-labs/omikuji-mcp-server

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio sunwood-ai-labs-omikuji-mcp-server node node_modules/@sunwood-ai-labs/omikuji-mcp-server/build/index.js

How to use

The omikuji MCP server provides a fortune-telling feature using MCP. It generates a random fortune (great blessing, blessing, middle blessing, end blessing, curse), includes a detailed fortune description, and offers today’s advice. You can also request a fortune for a specific name. The primary tool exposed by this server is draw_fortune, which you can invoke through your MCP client to obtain a formatted fortune response. When a name is provided, the fortune is generated and can be personalized accordingly; if no name is provided, the tool can still return a general fortune.

To use, ensure the omikuji MCP server is running and accessible through your MCP tooling. Call the draw_fortune action with a payload containing an optional name field. The server will return a structured fortune with the selected fortune type, explanation, and advice for the day. If you omit the name field, you will receive a generic fortune output.

How to install

Prerequisites:

  • Node.js (LTS version) and npm installed
  • Git installed

Installation steps:

  1. Install from npm
npm install @sunwood-ai-labs/omikuji-mcp-server
  1. Or clone from GitHub and install locally
git clone https://github.com/Sunwood-ai-labs/omikuji-mcp-server.git
cd omikuji-mcp-server
npm install
npm run build
  1. Run the MCP server locally (example)
# Ensure dependencies are installed
# Then start the server (adjust depending on your environment)
npm run start
  1. Add the MCP configuration (example)
{
  "mcpServers": {
    "omikuji": {
      "command": "node",
      "args": ["node_modules/@sunwood-ai-labs/omikuji-mcp-server/build/index.js"]
    }
  }
}

Additional notes

Notes and tips:

  • This package is experimental and leverages roo-cline for AI-assisted development. Unexpected behavior may occur; use in non-production environments.
  • If you encounter issues, open an issue on GitHub with details about your environment and steps to reproduce.
  • Environment variables are not required by default, but you can extend the MCP config with env entries if the server later needs API keys or feature flags.
  • License: MIT. Author: Sunwood AI Labs.
  • Ensure you build the project before running in production-like workflows, as the build step generates the index.js used by the MCP server.

Related MCP Servers

Sponsor this space

Reach thousands of developers