Skip to main content
Glama
Weather MCP Server

Weather MCP Server

Weather MCP Server

A complete Model Context Protocol (MCP) server that provides weather information through tools, resources, and prompts, designed for integration with Cursor IDE.

What is MCP (Model Context Protocol)?

MCP is a protocol that enables AI assistants (like Cursor) to connect to external data sources and tools. It allows AI models to:

  • Call Tools: Execute functions to perform actions (e.g., fetch weather data, query databases)

  • Read Resources: Access structured data from external sources (e.g., files, APIs, databases)

  • Use Prompts: Leverage reusable prompt templates for consistent interactions

How MCP Works

┌─────────────┐         MCP Protocol         ┌──────────────┐
│   Cursor    │ ◄──────────────────────────► │  MCP Server  │
│     IDE     │     (stdin/stdout or HTTP)    │  (Python)    │
└─────────────┘                               └──────────────┘
      │                                              │
      │  Calls tools, reads resources,              │
      │  uses prompts                               │
      │                                              │
      └──────────────────────────────────────────────┘
                    External APIs/Data

The MCP server acts as a bridge between the AI assistant and external services, providing a standardized interface for accessing data and functionality.

Related MCP server: Weather Prediction MCP Server

Features

This Weather MCP Server provides:

Tools

  • get_current_weather(location: str) - Fetch current weather conditions for a location

  • get_weather_forecast(location: str, days: int) - Get multi-day weather forecast

  • search_locations(query: str) - Search for location names

Resources

  • weather://current/{location} - Current weather data as a readable resource

  • weather://forecast/{location} - Forecast data as a readable resource

Prompts

  • analyze_weather - Template for analyzing weather patterns and conditions

  • compare_locations - Template for comparing weather between different locations

Setup

Prerequisites

  • Python 3.12 or higher

  • uv package manager (or pip)

Installation

  1. Install dependencies:

uv sync
# or
pip install -r requirements.txt
  1. Set up environment variables (optional, for real API):

    Create a .env file in the project root:

    # .env
    WEATHER_API_KEY=your_api_key_here

    Get a free API key from OpenWeatherMap

    Note: If no API key is provided, the server will use mock data for demonstration purposes.

Running the Server

python main.py

The server will start and communicate via stdio (standard input/output), which is the standard transport for MCP servers in Cursor IDE.

Cursor IDE Integration

To use this MCP server in Cursor IDE:

  1. Open Cursor IDE settings (Cmd/Ctrl + ,)

  2. Navigate to Features → MCP Servers (or search for "MCP" in settings)

  3. Click Add Server or edit the MCP servers configuration

  4. Add the following configuration (update the path to match your project location):

{
  "mcpServers": {
    "weather": {
      "command": "uv",
      "args": [
        "run",
        "python",
        "/Users/pratik/weather/main.py"
      ],
      "env": {}
    }
  }
}

Important: Replace /Users/pratik/weather/main.py with the absolute path to your main.py file.

  1. Save the configuration

  2. Restart Cursor IDE

  3. The AI assistant can now use the weather tools, resources, and prompts!

Alternative: You can also copy the configuration from cursor_mcp_config.json and merge it into your Cursor settings.

Usage Examples

Once integrated with Cursor IDE, you can ask the AI assistant:

  • "What's the weather in New York?"

  • "Get a 5-day forecast for London"

  • "Compare the weather in San Francisco and Seattle"

  • "Search for locations matching 'Paris'"

The AI will automatically use the appropriate MCP tools, resources, or prompts to fulfill your request.

Weather MCP Server Usage Example

Example: Asking "What's the weather in New York?" in Cursor IDE with the Weather MCP Server

Architecture

┌─────────────┐
│   Cursor    │
│     IDE     │
└──────┬──────┘
       │ MCP Protocol
       │
┌──────▼──────────────────┐
│   MCP Weather Server    │
│  (main.py)              │
├─────────────────────────┤
│ • Tools                 │
│ • Resources             │
│ • Prompts               │
└──────┬──────────────────┘
       │
┌──────▼──────────┐
│ Weather API     │
│ (weather_api.py)│
└─────────────────┘

Development

Project Structure

weather/
├── main.py                 # MCP server implementation
├── weather_api.py          # Weather API client
├── pyproject.toml          # Dependencies
├── cursor_mcp_config.json  # Cursor IDE configuration
├── .env.example            # Environment template
└── README.md               # This file

Adding New Features

  • New Tools: Add functions to the tools list in main.py

  • New Resources: Add URI patterns to the resources list in main.py

  • New Prompts: Add prompt templates to the prompts list in main.py

License

MIT

Available Tools

3 tools
get_current_weatherC

Get current weather conditions for a specific location

Inputs: location (required).

get_weather_forecastC

Get weather forecast for a specific location for multiple days

Inputs: location (required), days.

search_locationsC

Search for location names matching a query string

Inputs: query (required).

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap: get_current_weather retrieves current conditions, get_weather_forecast provides future predictions, and search_locations handles location queries. An agent can easily differentiate between these three functions.

    Naming Consistency5/5

    All tools follow a consistent verb_noun naming pattern (get_current_weather, get_weather_forecast, search_locations) with clear, descriptive names. There are no deviations in style or convention across the toolset.

    Tool Count4/5

    Three tools is reasonable for a weather server, covering core functions like current conditions, forecasts, and location search. However, it feels slightly thin as it lacks tools for historical weather data or alerts, which are common in weather APIs.

    Completeness4/5

    The toolset covers essential weather operations: retrieving current data, forecasts, and location lookup. A minor gap exists in not including historical weather data or severe weather alerts, but agents can still perform most common weather-related tasks effectively.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers