Skip to main content
Glama
GuardForever

Local Weather MCP Server

by GuardForever

本地 Dify 可用的 MCP Server(HTTP)

这是一个最小可用的 MCP Server,提供 2 个工具:

  • health:连通性检查

  • get_weather(location):按城市名查询当前天气

1)安装依赖

如果你有系统 Python:

pip install -r requirements.txt

如果你要使用 Codex 内置 Python 运行时:

C:\\Users\\86318\\.cache\\codex-runtimes\\codex-primary-runtime\\dependencies\\python\\python.exe -m pip install -r requirements.txt

Related MCP server: my-weather-server-0706

2)启动 MCP Server

python server.py

默认监听:

  • Host:0.0.0.0

  • Port:8787

  • MCP URL:http://127.0.0.1:8787/mcp

可选环境变量覆盖:

  • MCP_HOST

  • MCP_PORT

  • MCP_PATH

示例:

$env:MCP_PORT='8800'; python .\\server.py

3)在本地 Dify 接入

在 Dify 的 MCP Server(HTTP)配置里填写:

  • Server URL:http://127.0.0.1:8787/mcp

  • Name:local-weather

  • Server ID:local_weather

保存后,Dify 应该能自动发现以下工具:

  • health

  • get_weather

4)调用示例

在 Agent 或 Workflow 中让模型调用:

  • health

  • get_weather,参数 location = "Shanghai"

5)常见问题

  • 如果 Dify 运行在 Docker 容器里,127.0.0.1 指向容器本身,不是宿主机。

    • 通常改用:http://host.docker.internal:8787/mcp

  • 如果连接失败:

    • 检查端口 8787 是否被占用

    • 检查防火墙规则

    • 确认 URL 包含 /mcp 路径

Related MCP Connectors

Related MCP Servers

  • F
    license
    Not graded
    quality
    D
    maintenance
    Provides weather information through MCP tools integrated with a FastAPI backend, enabling users to query current weather for single or multiple cities and check API health status.
    -
  • A
    license
    A
    quality
    B
    maintenance
    MCP server that provides current weather for any city using Open-Meteo APIs. It exposes a single tool 'get_weather' returning temperature, humidity, wind, and other weather data.
    1
    11 npm
    MIT
  • F
    license
    Not graded
    quality
    B
    maintenance
    Provides weather query capabilities using the Open-Meteo API with a tool for city/coordinate weather and a weather resource URI.
    1
    -
  • A
    license
    Not graded
    quality
    C
    maintenance
    Provides real-time weather queries for 12 major Chinese cities and global cities using the wttr.in API, with tools like get_weather and list_supported_cities.
    1
    MIT