Weather MCP Server

mcp-name: io.github.isdaniel/mcp_weather_server

A Model Context Protocol (MCP) server that provides weather information using the Open-Meteo API. This server supports multiple transport modes: standard stdio, HTTP Server-Sent Events (SSE), and the new Streamable HTTP protocol for web-based integration.

Features

Weather & Air Quality

• Get current weather information with comprehensive metrics:
  • Temperature, humidity, dew point
  • Wind speed, direction, and gusts
  • Precipitation (rain/snow) and probability
  • Atmospheric pressure and cloud cover
  • UV index and visibility
  • "Feels like" temperature
  • Sunrise and sunset times (local time at the location)
• Get weather data for a date range with hourly details and daily sunrise/sunset times
• Get air quality information including:
  • PM2.5 and PM10 particulate matter
  • Ozone, nitrogen dioxide, carbon monoxide
  • Sulfur dioxide, ammonia, dust
  • Aerosol optical depth
  • Health advisories and recommendations

Time & Timezone

• Get current date/time in any timezone
• Convert time between timezones
• Get timezone information

Transport Modes

• Multiple transport modes:
  • stdio - Standard MCP for desktop clients (Claude Desktop, etc.)
  • SSE - Server-Sent Events for web applications
  • streamable-http - Modern MCP Streamable HTTP protocol with stateful/stateless options
• RESTful API endpoints via Starlette integration

Installation

Installing via Smithery

To install Weather MCP Server automatically via Smithery:

npx -y @smithery/cli install @isdaniel/mcp_weather_server

Standard Installation (for MCP clients like Claude Desktop)

This package can be installed using pip:

pip install mcp_weather_server

Manual Configuration for MCP Clients

This server is designed to be installed manually by adding its configuration to the cline_mcp_settings.json file.

1. Add the following entry to the mcpServers object in your cline_mcp_settings.json file:

{
  "mcpServers": {
    "weather": {
      "command": "python",
      "args": [
        "-m",
        "mcp_weather_server"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}

2. Save the cline_mcp_settings.json file.

HTTP Server Installation (for web applications)

For HTTP SSE or Streamable HTTP support, you'll need additional dependencies:

pip install mcp_weather_server starlette uvicorn

Server Modes

This MCP server supports stdio, SSE, and streamable-http modes in a single unified server:

Mode Comparison

1. Standard MCP Mode (Default)

The standard mode communicates via stdio and is compatible with MCP clients like Claude Desktop.

# Default mode (stdio)
python -m mcp_weather_server

# Explicitly specify stdio mode
python -m mcp_weather_server.server --mode stdio

2. HTTP SSE Mode (Web Applications)

The SSE mode runs an HTTP server that provides MCP functionality via Server-Sent Events, making it accessible to web applications.

# Start SSE server on default host/port (0.0.0.0:8080)
python -m mcp_weather_server --mode sse

# Specify custom host and port
python -m mcp_weather_server --mode sse --host localhost --port 3000

# Enable debug mode
python -m mcp_weather_server --mode sse --debug

SSE Endpoints:

• GET /sse - SSE endpoint for MCP communication
• POST /messages/ - Message endpoint for sending MCP requests

3. Streamable HTTP Mode (Modern MCP Protocol)

The streamable-http mode implements the new MCP Streamable HTTP protocol with a single /mcp endpoint. This mode supports both stateful (default) and stateless operations.

# Start streamable HTTP server on default host/port (0.0.0.0:8080)
python -m mcp_weather_server --mode streamable-http

# Specify custom host and port
python -m mcp_weather_server --mode streamable-http --host localhost --port 3000

# Enable stateless mode (creates fresh transport per request, no session tracking)
python -m mcp_weather_server --mode streamable-http --stateless

# Enable debug mode
python -m mcp_weather_server --mode streamable-http --debug

Streamable HTTP Features:

• Stateful mode (default): Maintains session state across requests using session IDs
• Stateless mode: Creates fresh transport per request with no session tracking
• Single endpoint: All MCP communication happens through /mcp
• Modern protocol: Implements the latest MCP Streamable HTTP specification

Streamable HTTP Endpoint:

• POST /mcp - Single endpoint for all MCP communication (initialize, tools/list, tools/call, etc.)

Command Line Options:

--mode {stdio,sse,streamable-http}  Server mode: stdio (default), sse, or streamable-http
--host HOST                          Host to bind to (HTTP modes only, default: 0.0.0.0)
--port PORT                          Port to listen on (HTTP modes only, default: 8080)
--stateless                          Run in stateless mode (streamable-http only)
--debug                              Enable debug mode

Example SSE Usage:

// Connect to SSE endpoint
const eventSource = new EventSource('http://localhost:8080/sse');

// Send MCP tool request
fetch('http://localhost:8080/messages/', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({
    type: 'tool_call',
    tool: 'get_weather',
    arguments: { city: 'Tokyo' }
  })
});

Example Streamable HTTP Usage:

// Initialize session and call tool using Streamable HTTP protocol
async function callWeatherTool() {
  const response = await fetch('http://localhost:8080/mcp', {
    method: 'POST',
    headers: {
      'Content-Type': 'application/json'
    },
    body: JSON.stringify({
      jsonrpc: '2.0',
      method: 'tools/call',
      params: {
        name: 'get_current_weather',
        arguments: { city: 'Tokyo' }
      },
      id: 1
    })
  });

  const result = await response.json();
  console.log(result);
}

Configuration

This server does not require an API key. It uses the Open-Meteo API, which is free and open-source.

Usage

This server provides several tools for weather and time-related operations:

Available Tools

Weather Tools

1. get_current_weather - Get current weather for a city with comprehensive metrics
2. get_weather_by_datetime_range - Get weather data for a date range with hourly details
3. get_weather_details - Get detailed weather information as structured JSON data

Air Quality Tools

4. get_air_quality - Get air quality information with pollutant levels and health advice
5. get_air_quality_details - Get detailed air quality data as structured JSON

Time & Timezone Tools

6. get_current_datetime - Get current time in any timezone
7. get_timezone_info - Get timezone information
8. convert_time - Convert time between timezones

Tool Details

get_current_weather

Retrieves comprehensive current weather information for a given city with enhanced metrics.

Parameters:

• city (string, required): The name of the city (English names only)

Returns: Detailed weather data including:

• Temperature and "feels like" temperature
• Humidity, dew point
• Wind speed, direction (as compass direction), and gusts
• Precipitation details (rain/snow) and probability
• Atmospheric pressure and cloud cover
• UV index with warning levels
• Visibility

Example Response:

The weather in Tokyo is Mainly clear with a temperature of 22.5°C (feels like 21.0°C),
relative humidity at 65%, and dew point at 15.5°C. Wind is blowing from the NE at 12.5 km/h
with gusts up to 18.5 km/h. Atmospheric pressure is 1013.2 hPa with 25% cloud cover.
UV index is 5.5 (Moderate). Visibility is 10.0 km.

get_weather_by_datetime_range

Retrieves hourly weather information with comprehensive metrics for a specified city between start and end dates.

Parameters:

• city (string, required): The name of the city (English names only)
• start_date (string, required): Start date in format YYYY-MM-DD (ISO 8601)
• end_date (string, required): End date in format YYYY-MM-DD (ISO 8601)