Advertise
MCP.so
Sign In

MCP US Weather Client/Server

@ankitmishralive

Repository

Basic information

Category

Developer Tools

Transports

stdio

Author

ankitmishralive

About MCP US Weather Client/Server

A simple MCP (Model Context Protocol) server that provides weather alert information for US states, leveraging the National Weather Service (NWS) API. It also includes an example client application that demonstrates how to interact with the MCP server using the mcp_use library.

#mcp#weather#api#client-server

MCP US Weather Client/Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "Hands-on-MCP": {
      "command": "uv",
      "args": [
        "run",
        "mcp",
        "dev",
        "server/weather.py"
      ]
    }
  }
}

MCP US Weather Client/Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP US Weather Client/Server?

This repository contains a simple MCP (Model Context Protocol) server that provides weather alert information for US states by leveraging the National Weather Service (NWS) API. It also includes an example client application demonstrating how to interact with the MCP server using the mcp_use library and Langchain.

How to use MCP US Weather Client/Server?

Clone the repository, install dependencies with uv add -r requirements.txt, and create a .env file with your Groq API key. Start the server with uv run mcp dev server/weather.py and the client with uv run server/client.py. At the client prompt, type queries such as "Get weather alerts for CA, NY or NJ" and use exit, quit, or clear to manage the conversation.

Key features of MCP US Weather Client/Server

  • Fetches active weather alerts for any US state
  • Built using the fastmcp library for MCP server implementation
  • Includes a client with conversation memory
  • Integrates with Langchain for LLM interaction
  • Provides a get_alerts tool and get_config resource
  • Uses the public National Weather Service API (api.weather.gov)

Use cases of MCP US Weather Client/Server

  • Query weather alerts for one or multiple US states via natural language
  • Learn how to build and run an MCP server with fastmcp
  • Explore MCP client integration with Langchain and conversation memory
  • Demonstrate a full MCP ecosystem with a real-world public API

Frequently asked questions

1

What tools and resources does the server expose?

The server exposes a `get_alerts` tool for fetching weather alerts by state and a `get_config` resource. These are defined in both the `weather.py` file and the `weather.json` configuration file.

2

What are the prerequisites and dependencies?

Python 3.7+, `uv` for dependency management, a Groq API key for the client, and the `mcp_use` library. The server itself connects to the public NWS API with no required authentication.

3

How do I configure the server and client?

Create a `.env` file in the root directory with `GROQ_API_KEY=<your_key>`. Ensure the `server/weather.json` file matches the tool and resource definitions in `server/weather.py`.

4

How do I run the server and client?

Start the server with `uv run mcp dev server/weather.py` and the client with `uv run server/client.py`. The client runs in an interactive prompt.

5

What data does the server use and where does it come from?

All weather alert data is fetched live from the National Weather Service API (api.weather.gov). No data is stored locally by the server.

Comments

More Developer Tools MCP servers

Modelglass

Modelglass

Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

1

Mythex

Mythex

Remote MCP server for Mythex, an AI app builder. Claude, Cursor or Codex get a cloud sandbox to build full-stack apps: files and bash, live preview, Postgres database, file storage, secrets, checkpoints, browser tests an

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

1

Mobbin

Mobbin

Mobbin MCP connects your AI agents to 600,000+ real product screens, so what they build starts with what already works.

SayLive

SayLIive

Publish the website your AI assistant just built, straight from the conversation. Static sites, your own domain, one payment, no subscription.

Advertise