MCP MCP Server

OpenWeather MCP — wraps the OpenWeatherMap API (openweathermap.org)

Local serverstdio

What is the MCP MCP server?

Connect MCP to Claude, Cursor or any other MCP client and it stops being a tab you switch to. OpenWeather MCP — wraps the OpenWeatherMap API (openweathermap.org). The mcp mcp server is what makes that connection.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • current_weather — Get the current weather for a city or coordinates: temperature, "feels like", conditions, humidity, wind speed, and cloud cover. Example
  • forecast — Get a multi-step weather forecast (3-hour intervals) for a city or coordinates: temperature, conditions, wind speed, and precipitation probability
  • air_quality — Get the current air quality for a set of coordinates: an air quality index (AQI, 1=Good to 5=Very Poor) plus pollutant component concentrations (CO
  • geocode — Resolve a place name (city, optionally with state/country) to geographic coordinates (latitude/longitude). Useful before calling air_quality, which

Installation

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Where it fits

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. MCP's toolset — current_weather, forecast, air_quality and 1 more — is a fair guide to whether it matches your workflow. It is maintained by mojibake-ai; worth a glance at recent repository activity before you build anything load-bearing on it.

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

Worth knowing first

  • 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.

Available tools

ToolWhat it does
current_weatherGet the current weather for a city or coordinates: temperature, "feels like", conditions, humidity, wind speed, and cloud cover. Example: current_weather({ city: "London", units: "metric" })
forecastGet a multi-step weather forecast (3-hour intervals) for a city or coordinates: temperature, conditions, wind speed, and precipitation probability over time. Example: forecast({ city: "Tokyo", count: 8 })
air_qualityGet the current air quality for a set of coordinates: an air quality index (AQI, 1=Good to 5=Very Poor) plus pollutant component concentrations (CO, NO2, O3, PM2.5, PM10, etc.). Example: air_quality({ lat: 51.5, lon: -0.
geocodeResolve a place name (city, optionally with state/country) to geographic coordinates (latitude/longitude). Useful before calling air_quality, which needs lat/lon. Example: geocode({ query: "Paris", limit: 5 })

How to install the MCP MCP server

{
  "mcpServers": {
    "openweather": {
      "url": "https://gateway.pipeworx.io/openweather/mcp"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use MCP to current weather.
  • Use MCP to forecast.
  • Use MCP to air quality.

Frequently asked questions

It connects MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (current_weather, forecast, air_quality, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with MCP directly.