KMB Bus MCP Server

What is KMB Bus MCP Server?

A Model Context Protocol (MCP) server that provides real-time access to Hong Kong's KMB (九龍巴士) and Long Win Bus (龍運巴士) route information and arrival times. It enables Language Models to query Hong Kong bus service information to answer user questions about bus routes, stops, and estimated arrival times.

How to use KMB Bus MCP Server?

Install via Smithery (npx -y @smithery/cli install @kennyckk/mcp_hkbus --client claude) or manually using uv. Configure the server in your MCP client (e.g., Claude Desktop) with the path to uv and the server script. Language Models can then call tools such as get_eta(), get_route_list(), get_stop_list(), get_route_stops(), find_stops_by_name(), and get_all_routes_at_stop().

Key features of KMB Bus MCP Server

• Real-time bus arrival information (ETA)
• Comprehensive bus route queries
• Bus stop information and searches
• Route-stop mapping
• Caching system to optimize API calls
• Bilingual support (English and Traditional Chinese)

Use cases of KMB Bus MCP Server

• Get estimated arrival times for a specific bus stop and route.
• Search for bus stops by name (English or Traditional Chinese).
• Retrieve all bus routes that serve a given stop.
• Look up the list of stops for a particular bus route.
• Obtain a full list of available bus routes or stops.

FAQ from KMB Bus MCP Server

What data source does KMB Bus MCP Server use?

It uses the official KMB/LWB Open Data API hosted at https://data.etabus.gov.hk/v1/transport/kmb.

What are the prerequisites for running KMB Bus MCP Server?

Python 3.10 or higher and the uv package manager are required.

How can I install KMB Bus MCP Server?

You can install it automatically via Smithery or manually by cloning the repository and running uv sync.

Does KMB Bus MCP Server support both English and Chinese?

Yes, it supports bilingual queries in English and Traditional Chinese for bus stop names and route information.

Are there any API rate limits?

The server relies on the KMB/LWB Open Data API. Users should be mindful of rate limits and implement appropriate error handling in production.