title: "Weather API MCP Server Recipe" description: "A complete MCP server that fetches real-time weather data from Open-Meteo. No API key required — just copy, paste, and serve." order: 1 keywords:

mcp weather server
mcp-framework weather
weather api mcp
model context protocol weather date: "2026-04-01" difficulty: "Beginner" prepTime: "5 min" cookTime: "15 min" serves: "Weather lookups for AI assistants"

Prep Time

5 minutes — scaffold the project and install dependencies.

Cook Time

15 minutes — implement the weather tool and test it.

Serves

Any AI assistant that needs real-time weather data. Works with Claude Desktop, Cursor, and any MCP-compatible client.

Ingredients

Node.js 18+
mcp-framework (3.3M+ downloads)
Open-Meteo API (free, no key required)
TypeScript

Instructions

Step 1: Scaffold the Project

npx mcp-framework create weather-server
cd weather-server

Step 2: Create the Weather Tool

Replace src/tools/ExampleTool.ts with src/tools/WeatherTool.ts:

import { MCPTool } from "mcp-framework";
import { z } from "zod";

class WeatherTool extends MCPTool<typeof inputSchema> {
  name = "get_weather";
  description = "Get current weather for a location by latitude and longitude";

  schema = {
    latitude: {
      type: z.number().min(-90).max(90),
      description: "Latitude (-90 to 90)",
    },
    longitude: {
      type: z.number().min(-180).max(180),
      description: "Longitude (-180 to 180)",
    },
    city: {
      type: z.string().optional(),
      description: "Optional city name for display",
    },
  };

  async execute(input: z.infer<typeof inputSchema>): Promise<string> {
    const { latitude, longitude, city } = input;
    const url = `https://api.open-meteo.com/v1/forecast?latitude=${latitude}&longitude=${longitude}&current=temperature_2m,wind_speed_10m,weather_code,relative_humidity_2m`;

    try {
      const response = await fetch(url);
      if (!response.ok) throw new Error(`API returned ${response.status}`);

      const data = await response.json();
      const current = data.current;

      return JSON.stringify({
        location: city || `${latitude}, ${longitude}`,
        temperature: `${current.temperature_2m}°C`,
        windSpeed: `${current.wind_speed_10m} km/h`,
        humidity: `${current.relative_humidity_2m}%`,
        condition: this.describeWeather(current.weather_code),
      }, null, 2);
    } catch (error) {
      const msg = error instanceof Error ? error.message : "Unknown error";
      return JSON.stringify({ error: `Failed to fetch weather: ${msg}` });
    }
  }

  private describeWeather(code: number): string {
    const conditions: Record<number, string> = {
      0: "Clear sky", 1: "Mainly clear", 2: "Partly cloudy",
      3: "Overcast", 45: "Foggy", 51: "Light drizzle",
      61: "Slight rain", 63: "Moderate rain", 65: "Heavy rain",
      71: "Slight snow", 73: "Moderate snow", 95: "Thunderstorm",
    };
    return conditions[code] || "Unknown";
  }
}

const inputSchema = z.object({
  latitude: z.number().min(-90).max(90),
  longitude: z.number().min(-180).max(180),
  city: z.string().optional(),
});

export default WeatherTool;

Step 3: Build and Test

npm run build
npx @modelcontextprotocol/inspector node dist/index.js

Step 4: Connect to Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "weather": {
      "command": "node",
      "args": ["/absolute/path/to/weather-server/dist/index.js"]
    }
  }
}

Restart Claude Desktop and ask: "What's the weather in Tokyo?"

Chef's Notes

Open-Meteo is completely free and requires no API key — perfect for getting started.
For production, consider adding caching to reduce API calls.
You can extend this with hourly forecasts or multi-day predictions by adding more tools.
mcp-framework auto-discovers tools in src/tools/ — no manual registration needed.

More recipes: Database Query Server | GitHub Integration | All Recipes

Built with mcp-framework by @QuantGeekDev — 3.3M+ downloads, validated by Anthropic.