Weather MCP Server

Weather MCP Server, giving LLMs weather forecast capabilities (current conditions, daily forecast, hourly data) via Open-Meteo (free, no API key required). That is what the weather mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

A Model Context Protocol (MCP) server that provides weather forecast data using the free Open-Meteo API.

• Current conditions — — temperature, feels-like, humidity, wind speed & direction
• Daily forecast — — high/low temperatures, precipitation probability, UV index, sunrise/sunset
• Hourly breakdown — — today's hour-by-hour temperatures and rain chance
• Free & keyless — — no API key required
• Multi-format — — text (human-readable) or json output

The tools it exposes

The server publishes 4 tools. What each one is for:

• get_forecast — Current conditions (day): Mainly clear Temperature: 27.2°C (feels like 27.2°C) Humidity: 0% Wind: 13.8 km/h S
• Cursor — The Cursor tool exposed by this server
• Windsurf — Add to ~/.config/windsurf/config.json or the workspace config:
• Smithery — Install via Smithery:

Getting it running

The server ships on npm as @atorresg/weather-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

How it compares

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Weather's toolset — get_forecast, Cursor, Windsurf and 1 more — is a fair guide to whether it matches your workflow. It is maintained by atorresg; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Weather's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

• It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
• Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.