Korea Realty
Korean real estate: court auctions, 10M+ MOLIT records, subscription notice facts, loan/DSR rules
作者提供的说明(英文原文)
Fast - accurate weather conditions and forecasts by city or coordinates.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"weather": {
"command": "npx",
"args": [
"-y",
"@jaredco/weather-mcp-server"
]
}
}
}在终端中运行这条命令
claude mcp add weather -- npx -y @jaredco/weather-mcp-server粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"weather": {
"command": "npx",
"args": [
"-y",
"@jaredco/weather-mcp-server"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"weather": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@jaredco/weather-mcp-server"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日
发布者(jaredco-ai)不是仓库所有者(jaredco);可能是其他人代为上架的
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 0 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(1.0.1)于8个月前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:Korea Realty, maviapi, GeoTok Trips
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Korean real estate: court auctions, 10M+ MOLIT records, subscription notice facts, loan/DSR rules
Live JSON from sites with no API (Booking, Airbnb, Tripadvisor…), plus agent-built APIs for any site
Plan trips: flights, hotels, transfers, sights and food spots from TikTok food videos.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Fast, reliable weather data for Claude and other MCP clients. Get current conditions and multi-day forecasts for any location worldwide.
🌐 Remote MCP Server (no install required) https://mcp-weathertrax.jaredco.com/mcp
Ask Claude:
“What’s the weather in Miami tomorrow?”
Claude will call the MCP weather server and return a forecast instantly.
Example API call:
curl -X POST https://mcp-weathertrax.jaredco.com/tools/weatherTool \
-H "Content-Type: application/json" \ -d '{"location":"Miami","query_type":"current"}'
In Claude or Claude Desktop, open Settings → Connectors → Add connector and use:
Name: WeatherTrax
URL: https://mcp-weathertrax.jaredco.com/mcp
You can now ask:
What’s the weather in New York this weekend?
curl https://mcp-weathertrax.jaredco.com/healthz
curl https://mcp-weathertrax.jaredco.com/.well-known/mcp/manifest
curl -X POST https://mcp-weathertrax.jaredco.com/tools/weatherTool \
-H "Content-Type: application/json" \ -d '{ "location": "San Francisco, CA", "query_type": "current" }'
Example response:
{
"summary": "It is currently 54°F and Clear in San Francisco.", "temp_high": 54, "temp_low": 54, "condition": "Clear", "wind": "5 mph W", "humidity": 65 }
curl -X POST https://mcp-weathertrax.jaredco.com/tools/weatherTool \
-H "Content-Type: application/json" \ -d '{ "location": "New York", "query_type": "multi_day", "num_days": 3 }'
Retrieve current weather or forecasts.
Input:
{
"location": "city name or coordinates", "query_type": "current | multi_day", "num_days": "optional forecast length" }
7-day planning forecast for outdoor work or events.
Input:
{
"location": "city or place", "context": "construction | travel | event", "timeframe": "optional timeframe hint" }
This server supports the full MCP JSON-RPC protocol.
Example tool call:
curl -X POST https://mcp-weathertrax.jaredco.com/mcp \
-H "Content-Type: application/json" \ -H "Accept: application/json, text/event-stream" \ -d '{ "jsonrpc":"2.0", "id":1, "method":"tools/call", "params":{ "name":"weatherTool", "arguments":{ "location":"London", "query_type":"current" } } }'
Run locally in one terminal:
npm install
npm start
In another terminal, run the protocol tests:
npm test
Release smoke suite:
npm run test:full
npm run test:full currently runs the same supported end-to-end smoke suite. The old pre-Streamable-HTTP regression harness remains available as npm run test:legacy; it is retained for reference and is not a release gate.
Set these server-side environment variables; never commit them:
| Variable | Required | Purpose |
|---|---|---|
WEATHER_API_KEY | Yes | World Weather Online API key. |
PORT | No | HTTP listener port; defaults to 3000. |
TRUST_PROXY | Production-dependent | Number of trusted reverse-proxy hops; set to 1 for a single known proxy. |
ALLOWED_ORIGINS | No | Comma-separated browser origins allowed to call MCP; defaults to https://claude.ai. |
The service exposes aggregate, non-identifying operational counters at /metrics. Do not place this endpoint behind a public dashboard without adding appropriate access control.
Privacy policy available at:
https://mcp-weathertrax.jaredco.com/privacy
Key points:
Clone the repo:
git clone https://github.com/jaredco/weather-mcp-server.git
cd weather-mcp-server npm install npm start
Server runs locally at:
http://localhost:3000
MIT License.
Built using the Model Context Protocol by Anthropic.
Weather data provided by World Weather Online.
Server: Production API Version: 1.0.1 MCP Protocol: 2025-03-26
Made with ☀️ for Claude and MCP