mcpField
M
MCP Weather Server Setup Guide

MCP Weather Server Setup Guide

Local
github.com/debanshu005Media & Design0Updated 81w ago
Repository

About MCP Weather Server Setup Guide

A setup guide for building and testing a weather MCP server with the MCP SDK and uv. It is aimed at developers who want to expose current weather lookup through a tool and inspect results during development.

Key features

  1. 01Project setup with uv
  2. 02Weather lookup by latitude and longitude
  3. 03Development testing with MCP Inspector

Use cases

  1. 01Create a local weather MCP server
  2. 02Test weather tool results during development

MCP support

The guide describes an MCP server with a `get_current_weather` tool that accepts latitude and longitude and returns weather data.

#mcp#weather#server#setup#guide

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

MCP Weather Server Setup Guide

This guide walks you through setting up and running a weather server using the MCP SDK and uv, a Rust-based Python package manager.

✅ Prerequisites

Make sure you have the following installed before proceeding:

  • Claude.ai account (any account type works — MCP is supported)
  • Claude Desktop App (available for macOS and Windows)
  • Code Editor (e.g., Visual Studio Code)
  • uv — A fast Python package manager written in Rust
Install uv:
macOS (via Homebrew):

brew install uv

Windows (via WinGet):

winget install --id=astral-sh.uv -e

⚙️ Project Setup

Follow these steps to create and configure the project environment:

  1. Create the project folder: mkdir mcp-server-weather cd mcp-server-weather

  2. Initialize a new uv project: uv init

  3. Create a virtual environment: uv venv

  4. Activate the virtual environment:

macOS / Linux: source .venv/bin/activate

Windows (PowerShell): .venv\Scripts\Activate.ps1

To deactivate the virtual environment: deactivate

  1. Install required packages: uv add "mcp[cli]" httpx

🚀 Running and Testing the MCP Server

  1. Start the MCP server in development mode: mcp dev server.py

  2. Open http://localhost:5173 in your browser

  3. In the MCP Inspector:

    • Click Connect
    • Go to the Tools tab
    • Click List Tools
    • Select get_current_weather
    • Enter latitude and longitude (e.g., 63.4463991, 10.8127596)
    • The Tool Result section will display the JSON weather data

  4. To stop the server: Ctrl+C

📝 Notes

  • Ensure your server script is named server.py and located in the root of your project.
  • The MCP Inspector is a helpful tool for interacting with and debugging tools during development.

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.