Weather India MCP

Weather India MCP

Provides real-time weather forecasts and alerts for Indian metro cities using Open-Meteo, with support for named city queries and email sharing of weather summaries.

Category
访问服务器

README

Weather India MCP

A Model Context Protocol (MCP) server that provides real-time weather forecasts and alerts for India's major metro cities, powered by the Open-Meteo API (free, no API key required).

Tools

Tool Description
get_forecast Current weather + 5-day forecast for any location by latitude/longitude
get_india_city_forecast Current weather + 5-day forecast for a named Indian metro city
get_india_weather_alerts Scans all Indian metros and returns active severe weather alerts
share_weather_via_email Fetches weather for a city or coordinates and emails a formatted summary to any address

Supported Cities

Mumbai, Delhi, Bengaluru, Hyderabad, Chennai, Kolkata, Ahmedabad, Pune, Jaipur, Lucknow, Chandigarh, Bhopal, Thiruvananthapuram, Guwahati, Patna

Alert Severity Levels

  • Extreme — temperature ≥ 45°C, cyclonic winds ≥ 90 km/h, violent rain/hail/thunderstorms
  • Severe — temperature ≥ 42°C, winds ≥ 60 km/h, heavy rain, dangerous heat+humidity
  • Moderate — temperature ≥ 40°C, winds ≥ 40 km/h, moderate rain/snow

Prerequisites

Setup

1. Clone and install dependencies

git clone https://github.com/YOUR_USERNAME/weather.git
cd weather
npm install

2. Build

npm run build

This compiles TypeScript to build/index.js and makes it executable.

3. Configure Cursor

Add the server to your Cursor MCP config at ~/.cursor/mcp.json:

{
  "mcpServers": {
    "weather": {
      "command": "node",
      "args": ["/absolute/path/to/weather/build/index.js"]
    }
  }
}

Replace /absolute/path/to/weather with the actual path where you cloned the repo (e.g. /Users/yourname/weather).

4. Restart Cursor

After saving mcp.json, restart Cursor or reload the window (Cmd+Shift+PReload Window). The three weather tools will appear under Settings → MCP.

Usage Examples

Once configured, you can ask your AI assistant things like:

  • "What's the weather in Mumbai right now?"
  • "Are there any severe weather alerts across Indian cities today?"
  • "Give me the 5-day forecast for Chennai."
  • "What's the weather at latitude 28.6, longitude 77.2?"
  • "Share the Bengaluru weather summary to myemail@gmail.com"

Demo

1. City Forecast — get_india_city_forecast

Ask for the weather in any supported Indian city and get current conditions plus a structured 5-day forecast.

Email share prompt in Cursor


2. Email Sharing — share_weather_via_email

Ask the assistant to share weather details to an email address. It fetches live data and dispatches a formatted summary instantly.

Weather email in Gmail inbox


3. Email Received

The recipient gets a clean HTML email with the city name, current conditions, and the full 5-day forecast — including any active weather alerts in the subject line.

City forecast for Bengaluru

Development

# Watch mode — auto-recompiles on save
npm run watch

Email Setup (for share_weather_via_email)

The email tool sends weather summaries via SMTP. Configure it in ~/.cursor/mcp.json under the weather server's env block:

"env": {
  "SMTP_HOST": "smtp.gmail.com",
  "SMTP_PORT": "587",
  "SMTP_USER": "your-gmail@gmail.com",
  "SMTP_PASS": "your-app-password",
  "SMTP_FROM": "Weather India MCP <your-gmail@gmail.com>"
}

For Gmail: Generate an App Password (requires 2FA enabled) and use it as SMTP_PASS. Your regular Gmail password will not work.

Works with any SMTP provider — just change SMTP_HOST and SMTP_PORT accordingly (e.g. Outlook, Zoho, custom SMTP).

No API Key Required

This server uses Open-Meteo, which is completely free and requires no authentication.

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