Skip to main content
Glama
Open-Meteo MCP Server

Open-Meteo MCP Server

by clarehancock

Open-Meteo MCP Server

一个基于 MCP(Model Context Protocol)的小型服务器,通过封装免费的 Open-Meteo API,让 Claude 等 AI 助手能够查询真实的天气数据——当前实况和预报。无需 API 密钥。

这是一个学习项目,用于端到端理解 MCP 服务器的工作原理:定义工具、本地运行,并将其连接到真实的 AI 客户端。

功能

连接到兼容 MCP 的客户端(如 Claude)后,它会暴露三个工具:

工具

作用

geocode_location

将地名(“London”)转换为坐标

get_current_weather

获取某个坐标的当前温度、风速、降水等

get_weather_forecast

获取某个坐标最长 16 天的预报(按天和/或按小时)

因此,用户可以问助手“里斯本明天天气怎么样?”,助手会自己调用这些工具来查询并回答——它并没有预先内置天气数据,而是实时获取。

Related MCP server: Weather MCP Server

构建方式

  • src/server.ts —— 定义这三个工具以及每个工具如何调用 Open-Meteo API。这是服务器真正的“大脑”。

  • src/index.ts —— 通过 stdio(标准输入/输出)运行服务器。这是本地开发工具(如 MCP Inspector)以及将服务器作为子进程启动的桌面应用所使用的传输方式。

  • src/http.ts —— 通过 Streamable HTTP 运行同一个服务器,因此可以通过网络访问——例如部署在某处,或从基于浏览器的客户端访问。这就是无需在本地安装任何东西即可演示的原因。

两个入口点共享 server.ts 中相同的工具定义,因此实际逻辑只存在于一个地方。

运行

npm install
npm run build

本地/stdio 模式(适用于将服务器作为子进程启动的工具):

npm start

HTTP 模式(用于连接远程客户端,例如通过转发的 Codespaces 端口或托管服务提供商):

node build/http.js

这会启动一个普通 HTTP 服务器,监听端口 3000(可通过 PORT 配置),在 POST /mcp 提供单个 MCP 端点,并附带 GET /health 检查。

无需客户端进行测试

MCP Inspector 的 CLI 模式是在终端中直接尝试的最快方式,无需浏览器:

# See what tools are available
npx @modelcontextprotocol/inspector --cli node build/index.js --method tools/list

# Actually call one
npx @modelcontextprotocol/inspector --cli node build/index.js \
  --method tools/call --tool-name geocode_location --tool-arg name=London

连接到 AI 助手

  • Claude Desktop / Claude Code:在客户端配置中将 build/index.js 指向为 stdio MCP 服务器。

  • Claude.ai 自定义连接器:指向正在运行的 HTTP 实例的 /mcp URL(需要支持自定义连接器的套餐)。

  • Anthropic API 直连:在 /v1/messages 请求的 mcp_servers 参数中传入 /mcp URL——这样任何自定义应用或页面都可以使用这些工具,而无需预先构建 MCP 客户端。

扩展说明

Open-Meteo 提供的变量和端点远多于本项目使用的(空气质量、海洋预报、历史/存档数据、集合预报)。若要添加更多,请遵循 src/server.ts 中现有工具的模式——注册一个新的 server.tool(...) 块,带上自己的输入 schema 和 Open-Meteo 请求。

数据 © Open-Meteo.com,CC BY 4.0。

Available Tools

3 tools
geocode_locationA

Look up geographic coordinates (latitude/longitude) for a place name, e.g. 'London', 'Paris, TX', or 'Tokyo'. Use this before calling the weather tools if you only have a place name rather than coordinates.

Inputs: name (required), count, language.

get_current_weatherA

Get the current weather conditions (temperature, wind, precipitation, etc.) for a specific latitude/longitude. Use geocode_location first if you only have a place name.

Inputs: latitude (required), longitude (required), timezone, wind_speed_unit, +1 more.

get_weather_forecastA

Get a multi-day hourly and/or daily weather forecast (up to 16 days) for a specific latitude/longitude. Use geocode_location first if you only have a place name. Defaults to a useful set of daily summary variables; pass include_hourly=true for hour-by-hour detail as well.

Inputs: latitude (required), longitude (required), timezone, forecast_days, +3 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.2/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: geocoding converts place names to coordinates, while the other two retrieve weather data. The current weather and forecast tools are differentiated by time horizon and description.

    Naming Consistency5/5

    All tool names follow a consistent snake_case verb_noun pattern: geocode_location, get_current_weather, get_weather_forecast. The naming style is uniform and predictable.

    Tool Count5/5

    With 3 tools, the server is tightly scoped for its purpose: location resolution, current conditions, and forecast. Each tool earns its place and the count feels complete without redundancy.

    Completeness4/5

    The core weather lookup flow is fully covered: geocode a place name, get current conditions, or get a forecast. Minor gaps exist such as historical weather data or alerts, but these are not essential for the apparent primary use case.

    Maintenance

    ActivityStale
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to fetch current weather conditions and forecasts for any city using the Open-Meteo API. Provides temperature, precipitation, and hourly forecast data through natural language queries.
      ISC
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to retrieve current weather, forecasts, and summaries for any global location using the Open-Meteo API, with no API key required.
      Creative Commons Zero v1.0 Universal
    • A
      license
      Not graded
      quality
      D
      maintenance
      Provides live weather data (current conditions, forecasts) and city geocoding through Open-Meteo API, enabling AI assistants to answer weather queries without an API key.
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables AI agents to retrieve real-time weather conditions and 7-10 day forecasts for any location via Open-Meteo, with no API key required.
      74 npm
      MIT