MCP Weather Aggregator
Provides AI-powered weather deduction using OpenAI's GPT-5-mini model to analyze differences between weather sources and deduce the most accurate values.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Weather Aggregator what's the weather in Tokyo?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Weather Aggregator
AI-powered weather aggregation from 6 sources with intelligent deduction using GPT-5-mini. Works as both a REST API for web apps and an MCP Server for AI assistants (Claude, Cursor, etc.).
โจ Features
๐ค๏ธ Multi-source aggregation - Open-Meteo, OpenWeatherMap, WeatherAPI, Visual Crossing, MET Norway (Yr.no), DWD (Bright Sky)
๐ค AI-powered deduction - GPT-5-mini analyzes differences and deduces most accurate values
๐ Dual Mode - Runs as REST API (FastAPI) or MCP Server (FastMCP)
๐จ Ambient theming - Dynamic gradients based on weather/time (sunny, rainy, storm, night, fog, sandstorm, blizzard, aurora...)
๐ง Advanced Data Processing - Uses EWMA (Exponential Smoothing) for forecast curves and Kalman Filter for sensor fusion
๐ Confidence scores - Based on source agreement (0-1)
๐ Forecasts - Daily (up to 16 days) + Hourly (24 hours)
๐ Astronomy - Sunrise/sunset, moon phases
๐ Multi-language - EN, CZ
๐ Geolocation - Automatic location detection with reverse geocoding (shows city name, not coordinates)
๐ Smart Caching - Redis-backed caching for geocoding (24h), weather data (30m), and aurora (1h)
๐ก๏ธ Security - Rate limiting, security headers, and input sanitization
๐ Aurora forecast - Real-time aurora borealis visibility prediction from NOAA data
Related MCP server: mcp-weather
๐ Quick Start
1. Configure API Keys
cp .env.example .envEdit .env:
# Required for AI deduction
OPENAI_API_KEY=sk-...
# Weather providers (add keys to enable more sources)
OPENWEATHERMAP_API_KEY=your_key # openweathermap.org
WEATHERAPI_KEY=your_key # weatherapi.com
VISUALCROSSING_KEY=your_key # visualcrossing.com2. Install Dependencies
This project uses uv for dependency management.
# Windows
curl -LsSf https://astral.sh/uv/install.ps1 | powershell -c -
# Install project dependencies
uv sync3. Run Application
Option A: Run as MCP Server (for AI Assistants)
Connect this server to your MCP client (Cursor, Claude Desktop, etc.).
# Run directly
uv run mcp-weather
# OR via python module
uv run python -m src.server
#### Option C: Run with Docker (Recommended)
Full stack (Backend + Frontend + Redis) in one command:
```bash
docker-compose up --buildFrontend: http://localhost:3000
Redis: localhost:6379
### 5. Configure Claude Desktop
To use this server with Claude Desktop, edit your config file:
- **Windows**: `C:\Users\USERNAME\AppData\Roaming\Claude\claude_desktop_config.json`
- **Mac/Linux**: `~/Library/Application Support/Claude/claude_desktop_config.json`
Add the following configuration (adjust path to your project):
```json
{
"mcpServers": {
"weather": {
"command": "C:\\Path\\To\\mcp-weather\\.venv\\Scripts\\python.exe",
"args": [
"-m",
"src.server"
],
"cwd": "C:\\Path\\To\\mcp-weather",
"env": {
"PYTHONPATH": "C:\\Path\\To\\mcp-weather"
}
}
}
}Note: The
PYTHONPATHenvironment variable is crucial for the server to find thesrcmodule correctly.
Available MCP Tools:
search_location(query)- Find coordinates for a cityget_current_weather(location_name)- Get current weather + AI summaryget_weather_forecast(location_name, days)- Full forecast + AI deductionget_weather_by_coordinates(lat, lon)- Weather for exact locationget_ambient_theme(location_name)- Get UI theme colors for current weatherget_aurora_forecast(location_name)- Aurora Borealis forecast & visibility
Option B: Run as REST API (for Frontend)
Starts the FastAPI server on http://localhost:8000.
# Run directly
uv run mcp-weather-api
# OR via python module
uv run python -m src.api4. Run Frontend
cd frontend
npm install
npm run devOpen http://localhost:3000 ๐
๐ก API Endpoints (REST Mode)
Endpoint | Method | Description |
| POST | Search locations by name |
| POST | Current weather + AI summary |
| POST | Full forecast + AI analysis |
| POST | Weather by lat/lon (auto-resolves city name) |
| POST | Aurora borealis forecast from NOAA |
| POST | Get ambient theme colors |
Example Request
curl -X POST http://localhost:8000/weather/forecast \
-H "Content-Type: application/json" \
-d '{"location_name": "Prague"}'Response includes:
current- Aggregated current weatherdaily_forecast- 7-day forecasthourly_forecast- 24-hour forecastai_summary- AI reasoning about the weatherconfidence- 0-1 score based on source agreementsources- List of providers usedambient_theme- Theme name + gradient colors
๐๏ธ Tech Stack
Component | Technology |
Backend | Python 3.14+, |
API Framework | FastAPI (REST) |
MCP Framework | FastMCP (MCP Server) |
Frontend | Next.js 16.1.4, Tailwind v4, shadcn/ui |
AI | OpenAI GPT-5-mini |
Weather | Open-Meteo (free), OpenWeatherMap, WeatherAPI, Visual Crossing |
๐ Project Structure
mcp-weather/
โโโ src/
โ โโโ api.py # FastAPI REST server
โ โโโ server.py # MCP Server (FastMCP)
โ โโโ aggregator.py # AI weather aggregation logic
โ โโโ models.py # Pydantic data models
โ โโโ providers/ # Weather API providers
โโโ frontend/ # Next.js app
โ โโโ src/
โ โโโ app/
โ โโโ components/weather/
โ โโโ lib/
โโโ .env # API keys
โโโ pyproject.toml # Python dependencies
โโโ uv.lock # Lock file๐ฎ Future Plans
NOAA Aviation Weather - METARs, TAFs, aviation advisories
NOAA Marine Weather - Ocean/coastal forecasts
NOAA Solar/Space - Enhanced UV index and solar radiation data
License
Copyright (c) 2026 Tomรกลก Stark
All rights reserved.
This code is provided for viewing purposes only. You may not copy, modify, distribute, or use this code, in whole or in part, without explicit written permission from the author.
Available Tools
6 toolsget_ambient_themeA
Get the ambient theme (colors/mood) for current weather conditions.
Args: location_name: Name of the city/location
Returns: JSON with theme name, gradient colors, and special effects
Inputs: location_name (required). Returns: result
get_aurora_forecastA
Get Aurora Borealis (Northern Lights) forecast and visibility probability.
Args: location_name: Name of the city/location (e.g. "Tromso", "Prague")
Returns: JSON with current Kp index, visibility probability, and 3-day forecast
Inputs: location_name (required). Returns: result
get_current_weatherA
Get current weather conditions with AI-powered summary.
Args: location_name: Name of the city/location (e.g., "Prague", "London") language: Language for AI summary (en, cs)
Returns: JSON with current weather, AI summary, and ambient theme
Inputs: location_name (required), language. Returns: result
get_weather_by_coordinatesA
Get weather forecast using exact coordinates with AI analysis.
Args:
latitude: Latitude of the location
longitude: Longitude of the location
days: Number of forecast days (1-16, default 7)
language: Language for AI summary (en, cs)
Returns: JSON with complete weather data, AI analysis, and ambient theme
Inputs: latitude (required), longitude (required), days, language. Returns: result
get_weather_forecastA
Get weather forecast with AI-powered analysis.
Args: location_name: Name of the city/location (e.g., "Prague", "London") days: Number of forecast days (1-16, default 7) language: Language for AI summary (en, cs)
Returns: JSON with forecast, AI analysis, and ambient theme
Inputs: location_name (required), days, language. Returns: result
search_locationA
Search for a location by name to get coordinates.
Args: query: City or location name to search for (e.g., "Prague", "New York")
Returns: JSON list of matching locations with name, country, latitude, longitude
Inputs: query (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
TDQS
Scored across 6 tools
Most tools target distinct resources, but get_weather_forecast and get_weather_by_coordinates are essentially the same forecast operation differentiated only by input, and get_ambient_theme duplicates a field already returned by the weather tools. Descriptions help clarify the intended usage, but the boundaries are not fully clean.
All tools use snake_case verb-first names, predominantly get_* plus search_location. The naming pattern is consistent and predictable across the entire set.
Six tools is an appropriate size for a weather aggregator, covering location lookup, current weather, forecasts, coordinate-based retrieval, ambient themes, and aurora forecasts. Each tool has a recognizable place in the overall workflow.
The core weather workflow is covered well: search locations, get current conditions, get forecasts, and use coordinates. Minor gaps like historical weather, weather alerts, or a dedicated current-weather-by-coordinates endpoint can be worked around but are not fatal.
Maintenance
Related MCP Connectors
MCP server for weather with reasoning โ umbrella advice, outdoor checks, city comparisons.
Hosted MCP server for Xweather weather data: conditions, forecasts, alerts, and more.
Weather, code search, currency & Solana trust scoring as MCP tools. Free, no API key needed.
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA Docker-based MCP server that provides current weather information for cities worldwide. Enables AI assistants like Claude to fetch temperature, weather conditions, and humidity data through a standardized interface.-
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol (MCP) server built with the mcp-framework to provide weather-related tools and data to AI clients. It enables integration of weather capabilities and custom tools into the MCP ecosystem for use with platforms like Claude Desktop.-

WeatherAI MCPofficial
AlicenseNot gradedqualityDmaintenanceWeatherAI MCP server โ 11 live weather tools for Claude Desktop, Cursor, Windsurf, and any MCP-compatible AI assistant38 npmMIT- AlicenseNot gradedqualityDmaintenanceA MCP server for querying real-time weather information for any city worldwide using the free Open-Meteo API, supporting CLI and integration with AI clients like Claude and Cursor.MIT