Check Korean Store Stock from Your Terminal

Ever needed to know if your local Daiso has that specific kitchen gadget in stock? Or maybe you're trying to see if the new popular cushion is available at Olive Young before you make the trip. Usually, this means opening a browser, navigating to a site, and clicking around. What if you could just ask your terminal?

Enter daiso-mcp, a clever little tool that brings real-time stock information for popular Korean stores right into your command line. It's a perfect example of a simple, focused utility that solves a very specific, sometimes frustrating, problem with minimal fuss.

What It Does

daiso-mcp is a command-line tool that fetches and displays the current stock levels for products at three major Korean chains: Daiso (the famous variety store), Olive Young (the beauty and health powerhouse), and CGV (the movie theater chain). You give it a product name or identifier, and it queries the respective service to tell you if it's available and at which locations.

It essentially automates the manual check you'd do on their websites or apps, packaging the result in a clean, scriptable format.

Why It's Cool

The clever part isn't just that it gets stock data—it's how it's built and what it enables. The tool is structured as a Model Context Protocol (MCP) server. MCP is a protocol that lets different tools and AI assistants talk to external data sources and functions. This means daiso-mcp isn't only a standalone CLI tool.

Its real power is integration. You can connect this MCP server to an AI coding assistant like Claude (via Claude Desktop) or other MCP-compatible clients. Once connected, you could literally ask your AI assistant in natural language: "Hey, check if the Rom&nd Zero Velvet Tint in 'Bare Fig' is in stock at Olive Young near me." The assistant uses daiso-mcp under the hood to get the answer and present it to you, all within your existing workflow.

It turns a niche data lookup into a composable piece of infrastructure for automation and AI. That's a developer-friendly approach.

How to Try It

You can run it directly as a CLI tool with Node.js. First, clone the repo and install dependencies:

git clone https://github.com/hmmhmmhm/daiso-mcp.git
cd daiso-mcp
npm install

Then, you can use it from the command line. The repository's README has the specific commands and required arguments for querying each store.

To unlock its more advanced, integrated potential, you'll want to run it as an MCP server and connect it to an MCP client. The project README provides a sample configuration snippet for Claude Desktop, which involves adding the server path to your Claude configuration file. After that, the tool's capabilities b