UBOS Asset Marketplace: Taiwan Central Weather Administration (CWA) MCP Server

Unlock the power of real-time and historical weather data for Taiwan with the Taiwan Central Weather Administration (CWA) MCP Server, now available on the UBOS Asset Marketplace. This powerful asset provides a seamless interface to the CWA API, enabling your AI Agents and applications to access crucial weather information for various use cases.

What is an MCP Server?

At its core, an MCP (Model Context Protocol) server acts as a crucial bridge. It allows AI models to access external data sources and tools. MCP is an open protocol that standardizes how applications provide context to LLMs. It simplifies the integration of AI with real-world information, making AI Agents more effective and context-aware.

Why the CWA MCP Server on UBOS?

The UBOS platform is a full-stack AI Agent development environment designed to bring AI Agents to every business department. Our platform help you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model and Multi-Agent Systems. With the CWA MCP Server on the UBOS Asset Marketplace, you gain:

• Seamless Integration: Effortlessly connect to Taiwan’s official weather data source using a standardized MCP interface.
• Simplified Data Access: The server handles data cleaning and format conversion, providing simplified API outputs with only essential information.
• Ready-to-Use Tools: Access three main tools – get_3_days_weather, get_1_week_weather, and get_historical_rainfall – designed for immediate use.
• Enhanced AI Agent Capabilities: Empower your AI Agents with real-time weather insights for improved decision-making and automation.
• UBOS Platform Advantage: Leverage the full capabilities of the UBOS platform for AI Agent orchestration, data connectivity, and custom model building.

Key Features

The CWA MCP Server boasts a rich set of features designed to streamline weather data access and integration:

• 3-Day & 1-Week Forecasts: Obtain detailed weather forecasts for all Taiwan counties and cities, providing essential information for short-term and medium-term planning.
• Historical Rainfall Data: Access historical rainfall data for the past three days, allowing for analysis of recent weather patterns.
• Automatic Data Cleaning & Conversion: Say goodbye to manual data wrangling. The server automatically cleans and converts data into a consistent and easy-to-use format.
• Simplified API Output: Receive streamlined API outputs containing only essential information, reducing complexity and improving efficiency.
• Comprehensive Weather Elements: Access a wide range of weather elements, including temperature, humidity, wind speed, precipitation probability, UV index, and more.
  • 3-Day Forecast: Temperature, Relative Humidity, Apparent Temperature, Comfort Index, Wind Direction, Wind Speed, 3-hour Precipitation Probability, Weather Phenomenon, Comprehensive Weather Description.
  • 1-Week Forecast: Average Temperature, Maximum Temperature, Minimum Temperature, Average Relative Humidity, Maximum Apparent Temperature, Minimum Apparent Temperature, Maximum Comfort Index, Minimum Comfort Index, Wind Speed, Wind Direction, 12-hour Precipitation Probability, UV Index, Weather Phenomenon, Comprehensive Weather Description.

Use Cases

The CWA MCP Server opens up a wide range of use cases across various industries:

• Agriculture: Provide farmers with accurate weather forecasts to optimize irrigation schedules, protect crops from adverse conditions, and improve yields. AI Agents can analyze the forecast data and proactively suggest actions to be taken.
• Logistics & Transportation: Optimize delivery routes based on real-time weather conditions, minimizing delays and ensuring timely deliveries. Integrate with AI-powered route optimization tools for dynamic adjustments.
• Tourism: Provide tourists with up-to-date weather information to help them plan their trips and activities, enhancing their overall experience. Offer personalized recommendations based on weather forecasts and user preferences.
• Disaster Management: Enhance disaster preparedness and response efforts with access to real-time rainfall data and weather forecasts, enabling timely warnings and evacuations. AI Agents can monitor weather patterns and automatically trigger alerts based on predefined thresholds.
• Energy Management: Optimize energy consumption based on weather forecasts, reducing costs and improving efficiency. Predict energy demand based on temperature and humidity forecasts, and adjust energy generation accordingly.
• Retail: Adjust inventory levels based on weather forecasts, ensuring that businesses have the right products in stock at the right time. For example, stock up on umbrellas and raincoats before a predicted rainfall event.
• Construction: Optimize construction schedules based on weather forecasts, minimizing delays and ensuring worker safety. Reschedule outdoor work activities during periods of heavy rain or strong winds.
• Environmental Monitoring: Monitor air quality and pollution levels based on weather conditions, providing valuable data for environmental protection efforts. Analyze the impact of weather patterns on air quality and develop strategies to mitigate pollution.

Getting Started

Integrating the CWA MCP Server into your UBOS environment is a breeze. Follow these simple steps:

1. Obtain an API Key: Request an API key from the Taiwan Central Weather Administration (CWA) through their Open Data Platform (https://opendata.cwa.gov.tw/index). Refer to the API Key Application Guide (https://www.hlbh.hlc.edu.tw/resource/openfid.php?id=38959) for detailed instructions.
2. Installation: Install the necessary dependencies using uv pip install -e .
3. Start the Server: Launch the server using the appropriate command for your operating system, providing your API key as an argument (e.g., uv --directory your_project_path run src/server.py your_API_key).
4. Access MCP Tools: Utilize the available MCP tools (get_3_days_weather, get_1_week_weather, get_historical_rainfall) to retrieve the desired weather data.

Example Usage

Here’s an example of how to use the get_3_days_weather tool to retrieve a 3-day weather forecast for Taipei City:

bash mcp invoke get_3_days_weather --location_name “Taipei City”

The server will return a JSON response containing detailed weather forecasts for Taipei City over the next three days.

Data Formats

The CWA MCP Server provides data in a structured JSON format for easy parsing and integration. Here’s a sample of the weather forecast data format:

[ { “ElementName”: “Temperature”, “Time”: [ [“2025-04-11T00:00”, “21”], [“2025-04-11T01:00”, “21”], … ] }, { “ElementName”: “Relative Humidity”, “Time”: [ [“2025-04-11T00:00”, “90”], [“2025-04-11T01:00”, “89”], … ] }, … ]

And here’s a sample of the rainfall data format:

{ “rain_labels”: [“Now”, “Past10Min”, “Past1hr”, “Past3hr”, “Past6Hr”, “Past12hr”, “Past24hr”, “Past2days”, “Past3days”], “stations”: [ { “name”: “Station Name”, “time”: “Observation Time”, “loc”: “County,Town”, “geo”: [latitude, longitude], “rain”: [current, past10min, past1hr, past3hr, past6hr, past12hr, past24hr, past2days, past3days] }, … ] }

System Requirements

To ensure optimal performance, the CWA MCP Server requires the following system specifications:

• Python 3.10+
• MCP CLI 1.6.0+
• uv package manager

Unlock the Power of Weather Data with UBOS

The Taiwan Central Weather Administration (CWA) MCP Server on the UBOS Asset Marketplace empowers you to seamlessly integrate real-time and historical weather data into your AI Agents and applications. Unlock new possibilities for automation, decision-making, and innovation across various industries. Join the UBOS ecosystem and harness the power of weather data today!