This project provides an AI-accessible interface to real-world retail and entertainment data, focusing on Korean chains like Daiso, Olive Young, and major cinema operators. It empowers AI agents (ChatGPT, Claude, Grok) to query product availability, store locations, and movie showtimes via the Model Context Protocol (MCP), offering users a convenient way to retrieve practical, location-aware information through natural language.

How It Works

The core of the project is its implementation of the Model Context Protocol (MCP), which standardizes access to diverse data sources. These MCP endpoints are hosted on Cloudflare Workers, presenting a unified API gateway (https://mcp.aka.page). This serverless architecture allows AI models to interact with services like Daiso product searches, Olive Young store lookups, and CGV movie schedules without needing direct integration with each individual service's API.

Quick Start & Requirements

• Primary Access: Connect AI assistants (e.g., Claude.ai, ChatGPT) via custom connector settings using the MCP server URL: https://mcp.aka.page. A dedicated GPT app is also available for mobile use at https://mcp.aka.page/prompt.
• CLI: Install and run via npx daiso.
• Prerequisites: Node.js is required for CLI usage. No specific hardware like GPUs is mentioned.
• Documentation: OpenAPI specifications are available at https://mcp.aka.page/openapi.json and https://mcp.aka.page/openapi-full.json.

Highlighted Details

• Extensive Retail & Cinema Coverage: Integrates data for Daiso, Olive Young, Lotte Mart, GS25, Seven Eleven, CU, E-mart24, Megabox, Lotte Cinema, and CGV.
• AI-Native MCP Protocol: Designed for seamless integration with AI agents, enabling natural language queries for practical information.
• Serverless Deployment: Utilizes Cloudflare Workers for scalable and accessible API hosting.
• High Code Coverage: Reports 100% code coverage, indicating a strong emphasis on testing.

Maintenance & Community

Notable contributors include @thecats1105 and @betterthanhajin. The project's Cloudflare Workers were last updated around March 17, 2026. No direct links to community forums (Discord/Slack) or a public roadmap are provided in the README.

Licensing & Compatibility

• License: MIT License.
• Compatibility: The MIT license permits broad use, including commercial applications and linking within closed-source projects.

Limitations & Caveats

• AI Support Gaps: Google Gemini and GitHub Copilot are explicitly not supported.
• API Facade: The default openapi.json serves as a facade for OpenAI Actions, potentially limiting direct use of all underlying service endpoints without accessing the full spec.
• Data Currency: Real-time data accuracy is dependent on the underlying services and the project's scraping/API interaction methods.