MCP Weather Alert Agent

MCP Weather Alert Agent

A lightweight AI agent that fetches real-time weather alerts for any U.S. state using the National Weather Service API.

Category
访问服务器

README

🌦️ MCP Weather Alert Agent

A lightweight AI agent powered by MCP (Modular Connector Protocol) that fetches real-time weather alerts for any U.S. state using the National Weather Service API.


✨ Features

  • 🤖 AI Chat Interface - Interactive conversation with memory
  • 🌪️ Real-time Weather Alerts - Live data from National Weather Service
  • Fast Inference - Powered by Groq LLM via LangChain
  • 🔧 MCP Integration - Built with mcp, mcp-use, and FastMCP
  • 🛠️ Tool-based Architecture - Structured function calling

🎯 Quick Example

💬 User: "Provide me weather alerts for California"
🤖 Agent: Calling get_alerts("CA")...
🌦️ Result: "FLOOD WARNING for Central Valley until 6 PM PST..."

🚀 Getting Started

Prerequisites

Installation

  1. Clone the repository

    git clone https://github.com/MokshadaRaibagkar/mcp-weather-alert-agent.git
    cd mcp-weather-alert-agent
    
  2. Create virtual environment

    python -m venv .venv
    source .venv/bin/activate  # Windows: .venv\Scripts\activate
    
  3. Install dependencies

    pip install -r requirements.txt
    
  4. Set up environment variables

    cp .env
    # Edit .env and add your GROQ_API_KEY
    

🛠️ Usage

Option 1: Interactive Chat Agent

uv run server/client.py

Option 2: MCP Dev Server (for testing)

uv run mcp dev server/weather.py

Opens MCP Inspector for tool testing and debugging.

Option 3: MCP Inspector (Visual Interface)

uv run mcp dev server/weather.py

🔧 API Reference

get_alerts(state: str) -> str

Fetches active weather alerts for a U.S. state.

Parameters:

  • state (str): Two-letter state code (e.g., "CA", "TX", "NY")

Returns:

  • Formatted string with current weather alerts or "No active alerts"

Example:

result = get_alerts("FL")
# Returns: "HURRICANE WARNING for Miami-Dade County..."

🧪 Example Interactions

Weather Alert Agent initialized! Ask me about weather alerts.

💬 You: What are the current weather alerts for Texas?
🛠️ Calling get_alerts with state: TX
🌦️ Current alerts for Texas:
- TORNADO WATCH for East Texas until 10 PM CDT
- FLASH FLOOD WARNING for Austin area until midnight

💬 You: Any alerts in California?
🛠️ Calling get_alerts with state: CA
✅ No active weather alerts for California at this time.

🌐 Tech Stack

Component Technology
MCP Framework MCP Protocol
LLM Groq
Agent Framework LangChain
Weather API National Weather Service
Development FastMCP

🤝 Contributing

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

👩‍💻 Author

Mokshada Raibagkar


<div align="center">

⭐ Star this repo if it helped you!

Made with ❤️ and ☕

</div>

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选