arthurpanhku

arthurpanhku / DragonMCP

Public

DragonMCP is a Model Context Protocol (MCP) server designed for AI Agents to interact with local life services in Greater China (Mainland China, HKSAR) and Asia. DragonMCP 是一个专为 AI Agent 设计的 Model Context Protocol (MCP) 服务器，旨在提供中国内地、中国香港及亚洲地区的本地生活服务接口。

ai-agents asia greatchina mcp mcp-server
22
5
100% credibility
Found Mar 11, 2026 at 14 stars -- GitGems finds repos before they trend. Get early access to the next one.
Sign Up Free
AI Analysis
TypeScript
AI Summary

DragonMCP is a Model Context Protocol (MCP) server that enables AI agents to interact with local life services in Greater China and Asia, such as querying MTR train schedules and Amap POIs and walking directions.

Star Growth

See how this repo grew from 14 to 22 stars Sign Up Free
Repurpose This Repo

Repurpose is a Pro feature

Generate ready-to-use prompts for X threads, LinkedIn posts, blog posts, YouTube scripts, and more -- with full repo context baked in.

Unlock Repurpose
AI-Generated Review

What is DragonMCP?

DragonMCP is a TypeScript MCP server designed for AI agents to interact with local life services in Greater China (mainland China, HKSAR) and Asia. It exposes tools like real-time MTR train schedules, Amap POI searches and directions (walking, driving, transit), HK weather reports, plus mocks for ride-hailing (Didi, Grab), payments (WeChat, Alipay, LinePay), food delivery (Meituan), and shopping (Taobao, Naver Maps). Running on Node.js with Docker support, it bridges the context gap so agents can handle regional "last-mile" tasks like booking rides or checking transit.

Why is it gaining traction?

Few MCP servers target China and Asia's fragmented APIs—MTR and Amap are live and reliable, unlike pure mocks elsewhere. Multilingual docs (English, Chinese, Japanese, Korean, French, German) lower barriers for regional devs, and SSE endpoints integrate seamlessly with Claude Desktop via simple config. The unified transit aggregator tool routes queries across regions, saving agent prompt engineering.

Who should use this?

AI agent builders targeting mainland China, HKSAR, or Asian users for transit, weather, or lifestyle apps. Devs prototyping e-commerce/payment flows with mocks before real API keys. Teams extending Claude or Qwen agents for local services like "next MTR from Admiralty" or Amap routes.

Verdict

Promising MVP for Asia-focused MCP agents, but 13 stars and 1.0% credibility reflect its beta status—mostly mocks, thin test coverage, Island/Tsuen Wan lines only. Fork and contribute real integrations if you're in the niche; skip for production without them.

(198 words)

Sign up to read the full AI review Sign Up Free

Similar repos coming soon.