mcpField
W
Weather MCP Server

Weather MCP Server

Local
github.com/ankushmehta123Media & Design0Updated 85w ago
Repository

About Weather MCP Server

Weather MCP Server connects AI assistants such as Claude to the National Weather Service API. It provides current alerts for US states and forecasts for specified coordinates.

Key features

  1. 01Retrieve active alerts by US state
  2. 02Fetch forecasts by latitude and longitude
  3. 03Expose weather tools through FastMCP

Use cases

  1. 01Check active weather alerts in a state
  2. 02Get a forecast for a location's coordinates

MCP support

It exposes tools that let MCP clients retrieve National Weather Service alerts and forecasts.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Weather MCP Server

Overview

This project implements a Model Context Protocol (MCP) server that allows AI assistants (such as Claude) to interact with the National Weather Service (NWS) API. The server provides real-time weather alerts and forecasts for a given location.

Features

  • Retrieve active weather alerts for a given US state.
  • Fetch weather forecasts for a specified latitude and longitude.
  • Implements the FastMCP framework to expose tools for AI interaction.

Technologies Used

  • Python
  • FastMCP
  • httpx (for asynchronous HTTP requests)

Prerequisites

Before running this project, ensure you have:

  • Python installed (version 3.11.6 or higher recommended)
  • uv package manager (pip install uv)
  • httpx installed (pip install httpx)
  • fastmcp installed (pip install fastmcp)
  • Claude Desktop app

uv Package Manager Installation

# On macOS and Linux.
curl -LsSf https://astral.sh/uv/install.sh | sh

# On Windows.
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Add to PATH

Installation & Setup

  1. Clone the repository: git clone https://github.com/ankushmehta123/weather-mcp-server.git

  2. Install dependencies: pip install -r requirements.txt

  3. Configure your MCP server by adding the following to claude_desktop_config.json:

     "mcpServers": {
     "weather": {
         "command": "C:/Users/"enter_your_username"/.local/bin/uv.exe",
         "args": [
             "--directory",
             "directory_location of main.py",
             "run",
             "main.py"
         ]
     }
 }
}

Usage

Run main.py python main.py

Available API Tools

Open Claude Desktop, you would see: 2 MCP tools available (at right-side of the search-bar)

README image

You can ask real-time weather-related questions to Claude now

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.