Weather MCP Server — Current, Forecast, Historical & Air Quality for AI Agents

Free-plan limit: Verified Apify free-plan runs can return up to 5 weather result records per run across all four tools. Paid-plan and local/unknown runs retain their existing behavior.

MCP server exposing 4 weather tools for AI agents. Connect Claude, Cursor, ChatGPT, n8n, OpenAI Agents SDK, or any MCP-compatible client to live weather data worldwide. No API key required.

What it does

This Actor runs a Model Context Protocol (MCP) server in Standby mode on the Apify platform. It exposes four agent-callable tools that fetch weather data from the free Open-Meteo API (no API key, commercially licensed):

Tool	What it returns
get_current_weather	Current temperature, feels-like, humidity, precipitation, cloud cover, pressure, wind speed/direction/gusts, day/night flag, weather description, and a one-line summary
get_weather_forecast	1–16 day forecast with per-day high/low temp, feels-like, precipitation, rain, snowfall, precipitation probability, wind, sunrise/sunset, UV index; optional hourly breakdown
get_historical_weather	Historical weather observations for any date range — per-day temp, precipitation, wind, sunshine duration
get_air_quality	Current air quality — PM10, PM2.5, CO, NO₂, SO₂, O₃, UV index, European AQI, US AQI, and category label (Good/Moderate/Unhealthy/etc.)

Use cases

• AI assistants querying current weather and multi-day forecasts for user-specified locations
• Travel and trip planning agents that need up-to-date conditions and short-term forecasts
• Logistics and supply chain automation checking weather along routes
• Agriculture and field-operations planning (frost risk, irrigation windows)
• Air quality monitoring and health advisory applications
• LLM-driven planning workflows that require weather context during reasoning
• n8n / Make / Zapier integrations for weather-triggered automations

How to use

Connect to Claude, Cursor, or any MCP client

Add the server to your MCP client configuration:

{
    "mcpServers": {
        "weather-mcp-server": {
            "url": "https://muhammadafzal--weather-mcp-server.apify.actor/mcp",
            "headers": {
                "Authorization": "Bearer <YOUR_APIFY_API_TOKEN>"
            }
        }
    }
}

Get your Apify API token from the Apify Console → Account → Integrations.

Call tools programmatically

Each tool accepts either a city name (location) or direct coordinates (latitude + longitude):

get_current_weather(location="London")
get_weather_forecast(location="Tokyo", forecastDays=5, includeHourly=true)
get_historical_weather(location="Berlin", startDate="2024-01-01", endDate="2024-01-31")
get_air_quality(location="Delhi")

Pricing

This Actor uses pay-per-event pricing. These are the current Apify Store event prices:

Event	Price (USD)	When it is charged
tool-call	$0.005	MCP Tool Call — Charged per MCP tool invocation.
apify-actor-start	$0.00005	Actor Start — Charged when the Actor starts running. Number of events charged depends on Actor memory (one event per GB, minimum one event). — Charged once per run.

Apify platform usage for this Actor run is included alongside the event prices above; no separate per-run platform-usage fee is passed to users.

This covers Apify platform usage for this Actor run. Other Apify products or usage outside this Actor run may still follow your account plan.

Data sources

• Open-Meteo Forecast API — free, no API key, commercially licensed
• Open-Meteo Historical Weather API — archive data from 1940 onwards
• Open-Meteo Air Quality API — CAMS-based air quality data
• Open-Meteo Geocoding API — city name → coordinates (OpenStreetMap-based)

No API keys, no logins, no rate limits beyond fair use.

Technical details

• Language: Python 3.12
• Framework: FastMCP + uvicorn
• Transport: Streamable HTTP (MCP standard)
• Mode: Standby (always-ready, auto-scales with demand)
• Endpoint: https://muhammadafzal--weather-mcp-server.apify.actor/mcp

Input

In Standby/MCP mode, tool calls are made through the /mcp endpoint — the Actor input is only used for batch-mode connectivity tests.

Field	Type	Default	Description
defaultLocation	string	""	City name for batch-mode test
defaultLatitude	number	0	Latitude for batch-mode test
defaultLongitude	number	0	Longitude for batch-mode test

Output

Each tool call returns a structured JSON object. The dataset also stores each tool call result for auditing.

Export scraped data, run the scraper via API, schedule and monitor runs, or integrate with other tools

Apify gives you access to the raw data, APIs, webhooks, and automation tools you need to build data pipelines. Export to JSON, CSV, Excel, or send to Google Sheets, Airtable, or any webhook via integrations.

Support

Found a bug or have a feature request? Open an issue on the Apify Store page.