hmmhmmhm/daiso-mcp
다이소를 MCP로! 뿐만 아니라 한국 로컬 리테일과 영화관 조회를 MCP, CLI, Codex Skill로 가능하게 해줍니다.
What it solves
This project provides a unified interface for AI agents to access real-time local information in South Korea, specifically for retail stores, convenience stores, cinema schedules, and fuel prices. It eliminates the need for users to manage multiple API keys for various local services, allowing AI to directly query product availability, store locations, and pricing.
How it works
It implements the Model Context Protocol (MCP), providing a set of tools that AI agents (like Claude, ChatGPT, and Grok) can call to fetch data. The system is deployed as a Cloudflare Worker and offers three primary access methods:
- MCP Server: A remote server (
https://mcp.aka.page) that connects directly to AI apps. - CLI: A command-line interface (
npx daiso) for manual queries or script integration. - Codex Skill: A specialized configuration for agents to use the CLI tool.
It aggregates data from various sources including Daiso, Olive Young, Lotte Mart, GS25, CU, 7-Eleven, Emart24, CGV, Megabox, and Lotte Cinema, and normalizes the responses into a standard format for consistent AI processing.
Who it’s for
- AI Agent Users: People who want their AI assistants to check local Korean retail inventory, find nearby cafes, or check movie times.
- Developers: Those looking to integrate Korean local retail and lifestyle data into their own AI applications via MCP or REST APIs.
Highlights
- Broad Retail Coverage: Supports product and inventory checks for major Korean retailers (Daiso, Olive Young, Lotte Mart) and all major convenience stores.
- Real-time Cinema Data: Accesses theater locations, movie lists, schedules, and remaining seats for CGV, Megabox, and Lotte Cinema.
- Fuel Price Integration: Provides national average prices and finds the cheapest gas stations via the Opinet API.
- Cross-Retailer Comparison: Includes a tool to compare prices for the same product across different convenience stores and Daiso.
- Zero-Config Setup: Users can connect the remote MCP server to AI apps without needing their own API keys.
相关
- 项目
- 项目
- 项目
- 项目
- 项目