mcpField
J
Juhe Weather MCP Server

Juhe Weather MCP Server

Local
github.com/juhemcpMedia & Design0Updated 84w ago
Repository

About Juhe Weather MCP Server

Juhe Weather MCP Server provides weather forecasts for cities and districts in China through the Juhe weather API. It is intended for MCP clients that need to retrieve local weather by place name.

Key features

  1. 01Query local weather by place name
  2. 02Support city and district names
  3. 03Return forecast content

Use cases

  1. 01Check the weather in a city
  2. 02Retrieve weather for a district
  3. 03Answer place-specific weather questions

MCP support

It exposes a query_weather tool to MCP clients, which accepts a city or district name and returns weather forecast content. The server requires a JUHE_WEATHER_API_KEY.

#jweather#weather-server#weather-api#juhemcp#weather#mcp-server

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "jweather": {
      "command": "uvx",
      "args": [
        "jweather-mcp-server"
      ]
    }
  }
}
Run commanduvx jweather-mcp-server

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypijweather-mcp-server

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

Juhe Weather MCP Server

一个提供全国天气预报查询功能的模型上下文协议（Model Context Protocol）服务器。该服务器使大型语言模型（LLMs）能够获取全国城市、地区的天气预报情况。

Components

Tools

服务器实现了一个工具:

  • query_weather: 根据城市、地区、区县名称查询当地实时天气预报情况.
    • 需要传入 "city"（城市、区县等名称）作为必须的字符串参数。
async def query_weather(
    city: str = Field(description="查询的城市名称，如北京、上海、广州、深圳、泰顺等；城市或区县或地区名使用简写，严格按照规范填写，否则会导致查询失败")
) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:

Install

This server requires Python 3.10 or higher. Install dependencies using uv (recommended) or pip

Using uv (recommended)

When using uv no specific installation is needed. We will use uvx to directly run jweather-mcp-server.

uvx jweather-mcp-server
Using PIP

Alternatively you can install jweather-mcp-server via pip:

pip install jweather-mcp-server

After installation, you can run it as a script using:

python -m jweather_mcp_server
Configuration
Environment Variables

JUHE_WEATHER_API_KEY: 聚合数据的天气预报查询API密钥。获取：https://www.juhe.cn/docs/api/id/73

JUHE_WEATHER_API_KEY=your_api_key
Configure For CLINE
Using uvx 
"mcpServers": {
  "jweather-mcp-server": {
    "command": "uvx",
    "args": [
      "jweather-mcp-server"
    ],
    "env": {
      "JUHE_WEATHER_API_KEY": "your_api_key"
    }
  }
}
Using pip installation 
"mcpServers": {
  "jweather-mcp-server": {
    "command": "python",
    "args": [
      "-m",
      "jmobile_location_mcp_server"
    ],
    "env": {
      "JUHE_WEATHER_API_KEY": "your_api_key"
    }
  }
}

Debugging

You can use the MCP inspector to debug the server. For uvx installations:

npx @modelcontextprotocol/inspector uvx jweather-mcp-server

Or if you've installed the package in a specific directory or are developing on it:

cd path/to/servers/src/jweather-mcp-server
npx @modelcontextprotocol/inspector uv run jweather-mcp-server

Examples of Questions for Cline

  1. "查询下苏州的天气"
  2. "今天上海的天气如何？"

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.