No install? Use cloud.anythingmcp.com directly.
Sign in, install the OpenWeather in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Query OpenWeather (current weather, forecasts, air quality, geocoding) from any AI agent. 6 tools, API-key auth.
💡 Keine Installation? Nutze cloud.anythingmcp.com direkt. Einloggen, Connectors → OpenWeather klicken, Zugangsdaten einfügen, MCP-API-Key erzeugen — fertig. Kein Docker, kein
git clone, kein lokaler Server.
OpenWeather + Gemini
Query OpenWeather (current weather, forecasts, air quality, geocoding) from any AI agent. 6 tools, API-key auth.
Voraussetzungen
Die vollständige Setup-Anleitung ist in den Connector eingebaut (im Store sichtbar, wenn du den Connector auswählst). Benötigte Umgebungsvariablen für diesen Connector:
OPENWEATHER_API_KEY
Schritt 1 — Zugangsdaten holen
This connector wraps the OpenWeather REST API (api.openweathermap.org).
Setup:
- Sign up at https://openweathermap.org/users/sign_up (free tier: 60 calls/min, 1M/month).
- Go to https://home.openweathermap.org/api_keys → copy the default key OR create a new one labelled e.g.
mcp. - Wait ~10 minutes — new keys take time to activate on the free tier.
- Set
OPENWEATHER_API_KEY.
Authentication: every request takes appid=${OPENWEATHER_API_KEY} as a query string. The adapter injects it automatically — never include it in tool arguments.
…(continued in the in-app connector instructions)
Schritt 2 — Adapter installieren
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Schritt 3 — Connector in Gemini hinzufügen
Gemini CLI liest MCP-Server aus ~/.gemini/settings.json (oder %APPDATA%\gemini\settings.json unter Windows). Hinzufügen:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Hole deinen MCP API Key aus AnythingMCP → Profil → MCP API Keys → Neuer Key.
- Speichern und
geminineu starten. /mcpin Gemini CLI ausführen —OpenWeathersollte als verfügbar gelistet sein.- Vertex AI Studio:
https://cloud.anythingmcp.com/mcpimtools-Array der Anfrage mit demselben Bearer-Header übergeben.
Verfügbare Tools
| Tool | What it does |
|---|---|
openweather_geocode_city | Translate a city name (optionally with state and country code) into latitude/longitude |
openweather_reverse_geocode | Translate latitude/longitude back into a list of nearby place names |
openweather_current_weather | Current weather at given coordinates: temperature, humidity, wind, conditions, sunrise/sunset |
openweather_forecast_5day | 5-day weather forecast at 3-hour intervals |
openweather_air_pollution | Current air-quality index (AQI 1-5) + concentrations of CO, NO, NO2, O3, SO2, PM2 |
openweather_air_pollution_forecast | Hourly air-pollution forecast for the next ~4 days at given coordinates |
FAQ
Unterstützen Gemini 1.5 Pro oder 2.x MCP? Ja — Gemini CLI ≥ 0.4 und die Vertex AI Tools API akzeptieren MCP httpUrl-Connectors mit Bearer-Header.
Nächste Schritte
War dieser Guide hilfreich?