HK Climate and Weather MCP Server
Provides access to Hong Kong climate and weather data from the Hong Kong Observatory, including current conditions, forecasts, warnings, tides, and more.
README
HK Climate and Weather MCP Server
This is an MCP server that provides access to climate and weather data through a FastMCP interface.
Data Source
- Hong Kong Observatory
Features
- Current weather: Get current weather observations from HKO (supports optional region parameter)
- 9-day forecast: Get extended weather forecast including general situation, daily forecasts, sea and soil temperatures
- Local weather forecast: Get short-term weather forecast with outlook
- Weather warnings: Get summary and detailed information about active weather warnings
- Special weather tips: Get important weather-related safety tips
API Reference
Current Weather
get_current_weather(region: str = "Hong Kong Observatory") -> Dict
- Get current weather observations for a specific region in Hong Kong
- Parameters:
- region: The region to get weather for (default: "Hong Kong Observatory")
- Returns:
- Dict containing:
- warning: Current weather warnings
- temperature: Current temperature in Celsius
- humidity: Current humidity percentage
- rainfall: Current rainfall in mm
- Dict containing:
9-Day Weather Forecast
get_9_day_weather_forecast(lang: str = "en") -> Dict
- Get the 9-day weather forecast for Hong Kong
- Parameters:
- lang: Language code (en/tc/sc, default: en)
- Returns:
- Dict containing:
- generalSituation: General weather situation
- weatherForecast: List of daily forecast dicts
- updateTime: Last update time
- seaTemp: Sea temperature info
- soilTemp: List of soil temperature info
- Dict containing:
Local Weather Forecast
get_local_weather_forecast(lang: str = "en") -> Dict
- Get local weather forecast for Hong Kong
- Parameters:
- lang: Language code (en/tc/sc, default: en)
- Returns:
- Dict containing:
- forecastDesc: Forecast description
- outlook: Outlook forecast
- updateTime: Last update time
- forecastPeriod: Forecast period
- forecastDate: Forecast date
- Dict containing:
Weather Warning Summary
get_weather_warning_summary(lang: str = "en") -> Dict
- Get weather warning summary for Hong Kong
- Parameters:
- lang: Language code (en/tc/sc, default: en)
- Returns:
- Dict containing:
- warningMessage: List of warning messages
- updateTime: Last update time
- Dict containing:
Weather Warning Information
get_weather_warning_info(lang: str = "en") -> Dict
- Get detailed weather warning information
- Parameters:
- lang: Language code (en/tc/sc, default: en)
- Returns:
- Dict containing:
- warningStatement: Warning statement
- updateTime: Last update time
- Dict containing:
Special Weather Tips
get_special_weather_tips(lang: str = "en") -> Dict
- Get special weather tips for Hong Kong
- Parameters:
- lang: Language code (en/tc/sc, default: en)
- Returns:
- Dict containing:
- specialWeatherTips: List of special weather tips
- updateTime: Last update time
- Dict containing:
Visibility Data
get_visibility(lang: str = "en") -> Dict
- Get latest 10-minute mean visibility data for Hong Kong
- Parameters:
- lang: Language code (en/tc/sc, default: en)
- Returns:
- Dict containing visibility data with fields and data arrays
Lightning Data
get_lightning_data(lang: str = "en") -> Dict
- Get cloud-to-ground and cloud-to-cloud lightning count data
- Parameters:
- lang: Language code (en/tc/sc, default: en)
- Returns:
- Dict containing lightning data with fields and data arrays
Moon Times
get_moon_times(year: int, month: Optional[int] = None, day: Optional[int] = None, lang: str = "en") -> Dict
- Get times of moonrise, moon transit and moonset
- Parameters:
- year: Year (2018-2024)
- month: Optional month (1-12)
- day: Optional day (1-31)
- lang: Language code (en/tc/sc, default: en)
- Returns:
- Dict containing moon times data with fields and data arrays
Hourly Tides
get_hourly_tides(station: str, year: int, month: Optional[int] = None, day: Optional[int] = None, hour: Optional[int] = None, lang: str = "en") -> Dict
- Get hourly heights of astronomical tides for a specific station
- Parameters:
- station: Station code (e.g. 'CCH' for Cheung Chau)
- year: Year (2022-2024)
- month: Optional month (1-12)
- day: Optional day (1-31)
- hour: Optional hour (1-24)
- lang: Language code (en/tc/sc, default: en)
- Returns:
- Dict containing tide data with fields and data arrays
High/Low Tides
get_high_low_tides(station: str, year: int, month: Optional[int] = None, day: Optional[int] = None, hour: Optional[int] = None, lang: str = "en") -> Dict
- Get times and heights of astronomical high and low tides
- Parameters:
- station: Station code (e.g. 'CCH' for Cheung Chau)
- year: Year (2022-2024)
- month: Optional month (1-12)
- day: Optional day (1-31)
- hour: Optional hour (1-24)
- lang: Language code (en/tc/sc, default: en)
- Returns:
- Dict containing tide data with fields and data arrays
Weather and Radiation Report
get_weather_radiation_report(date: str, station: str, lang: str = "en") -> Dict
- Get weather and radiation level report for Hong Kong
- Parameters:
- date: Mandatory date in YYYYMMDD format (e.g., 20250618)
- station: Mandatory station code (e.g., 'HKO' for Hong Kong Observatory)
- lang: Language code (en/tc/sc, default: en)
- Returns:
- Dict containing weather and radiation data or error message if parameters are invalid
Station Codes
get_radiation_station_codes() -> Dict
- Get a list of station codes and their corresponding names for weather and radiation reports in Hong Kong
- Parameters:
- None
- Returns:
- Dict mapping station codes to station names
Setup
- Clone this repository
- Install Python dependencies:
pip install -r requirements.txt - Run the server:
python server.py
Running Options
- Default stdio mode:
python server.py - SSE mode (port 8000):
python server.py --sse
Environment Variables
TRANSPORT_MODE: Set tosseto run the server in SSE mode. If not set, defaults tostdiomode.HOST: WhenTRANSPORT_MODEissse, specifies the host to bind the server to (e.g.,0.0.0.0). Defaults to127.0.0.1.PORT: WhenTRANSPORT_MODEissse, specifies the port to run the server on (e.g.,8080). Defaults to8000.
Example:
TRANSPORT_MODE=sse HOST=0.0.0.0 PORT=8080 python server.py
Cline Integration
To connect this MCP server to Cline using stdio:
- Add this configuration to your Cline MCP settings (cline_mcp_settings.json):
{
"hko-server": {
"disabled": false,
"timeout": 3,
"type": "stdio",
"command": "python",
"args": [
"-m",
"hkopenai.hk_climate_mcp_server"
]
}
}
Testing
Tests are available in tests. Run with:
pytest
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.