SuperAPI AI Directory

hko-mcp

Basic demo of fetching weather from the Hong Kong Observatory.

Open website

About this tool

hko-mcp (also known as mcp-hko) is a server based on the Model Context Protocol (MCP), designed to provide access to the Hong Kong Observatory weather data API. It implements various tools that allow clients to retrieve weather forecasts, earthquake information, tide data, and other meteorological information through MCP.

Main Capabilities

The weather data tools provided by this server include:

  • 9-day Weather Forecast (fnd)
  • Current Weather Report (rhrread)
  • Local Weather Forecast (flw)
  • Weather Warning Information (warningInfo)
  • Weather Warning Summary (warnsum)
  • Special Weather Tips (swt)
  • Quick Earthquake Messages (qem)
  • Locally Felt Earth Tremor Report (feltearthquake)
  • Tide Information (HHOT, HLT)
  • Astronomical Data (SRS, lunardate)
  • Lightning and Visibility Data (LHL, LTMV)
  • Temperature Records (CLMTEMP, CLMMAXT, CLMMINT)
  • Radiation Level Reports (RYES)
  • Rainfall Data (hourlyrainfall)

Usage

Users can use these tools through natural language queries, for example:

  • Get the 9-day weather forecast: ask "what is the weather in next Wed ?"
  • Get the current weather report: ask "what is the weather now ?"

Development and Configuration

The project includes development setup instructions, including installing dependencies, starting the MCP development server, building the MCP server, and running tests in watch mode. Comprehensive tests have been created for all API functions; see docs/TESTING.md for details. The projectalso provides configuration instructions for Claude Desktop and Docker.

Project Structure

  • src/: server source code
  • src/lib/: API implementation modules
  • documentation/: API documentation and test cases
  • scripts/: development utilities
  • src/tests/: test files

Server Architecture

The MCP server is built on the FastMCP framework and implements various tools corresponding to the Hong Kong Observatory API. The architecture is shown through two diagrams: server overview and detailed tool structure.

Limitations

Currently, no information is provided regarding fees, pricing, platform restrictions, or specific usage outcomes.