JMA Data MCP

JMA Data MCP

Provides access to Japan Meteorological Agency (JMA) weather data including real-time observations, historical weather data, and forecasts from 1286 AMeDAS stations across Japan.

Category
访问服务器

README

JMA Data MCP

Japan Meteorological Agency (JMA) data MCP server.

Features

  • AMeDAS (Automated Meteorological Data Acquisition System) station data
  • 1286 observation stations across Japan
  • Search by station code, name, or location
  • Real-time weather observation data (temperature, humidity, wind, precipitation, etc.)
  • Historical weather data (past 1-2 weeks)
  • Time series data for trend analysis
  • Weather forecast by prefecture

Data Source

  • AMeDAS station data: https://www.jma.go.jp/bosai/amedas/
  • Real-time observation: https://www.jma.go.jp/bosai/amedas/
  • Weather forecast: https://www.jma.go.jp/bosai/forecast/

Installation

uv tool install git+https://github.com/koizumikento/jma-data-mcp.git

Or install locally:

git clone https://github.com/koizumikento/jma-data-mcp.git
cd jma-data-mcp
uv sync

MCP Server Configuration

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):

Installed version:

{
  "mcpServers": {
    "jma-data-mcp": {
      "command": "jma-data-mcp"
    }
  }
}

Direct from GitHub:

{
  "mcpServers": {
    "jma-data-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/koizumikento/jma-data-mcp.git",
        "jma-data-mcp"
      ]
    }
  }
}

Local development:

{
  "mcpServers": {
    "jma-data-mcp": {
      "command": "uv",
      "args": [
        "run",
        "--directory",
        "/path/to/jma-data-mcp",
        "jma-data-mcp"
      ]
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project root:

{
  "mcpServers": {
    "jma-data-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/koizumikento/jma-data-mcp.git",
        "jma-data-mcp"
      ]
    }
  }
}

Cline

Add to Cline MCP settings:

{
  "mcpServers": {
    "jma-data-mcp": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/koizumikento/jma-data-mcp.git",
        "jma-data-mcp"
      ]
    }
  }
}

Available Tools

Station Tools

  • get_station_info - Get station by code
  • search_stations - Search stations by name
  • search_nearby_stations - Search stations within radius
  • get_stations_of_type - Get stations by type (A-F)
  • list_stations - List all stations with pagination

Weather Tools

  • get_current_weather - Get current weather observation from AMeDAS
  • get_weather_by_location - Get weather from nearest station to coordinates
  • get_forecast - Get weather forecast for a prefecture
  • list_prefectures - List available prefecture codes

Historical Data Tools

  • get_historical_weather - Get weather data for a specific past date/time (available for ~1-2 weeks)
  • get_weather_time_series - Get time series data for trend analysis (hourly data up to 1 week)

Weather Data

The get_current_weather tool returns:

Field Description Unit
temperature Air temperature
humidity Relative humidity %
pressure Station pressure hPa
sea_level_pressure Sea level pressure hPa
wind.speed Wind speed m/s
wind.direction Wind direction 16 directions
precipitation.10min 10-min precipitation mm
precipitation.1h 1-hour precipitation mm
precipitation.3h 3-hour precipitation mm
precipitation.24h 24-hour precipitation mm
sunshine.1h 1-hour sunshine hours
snow.depth Snow depth cm
snow.1h/6h/12h/24h Snowfall cm

Station Types

Type Description
A Staffed observatory (官署)
B Special regional weather station (特別地域気象観測所)
C AMeDAS station (アメダス)
D Rain gauge station (雨量観測所)
E Snow depth station (積雪観測所)
F Regional rain station (地域雨量観測所)

Examples

Get current weather in Tokyo

Tool: get_current_weather
Arguments: {"station_code": "44132"}

Get weather by coordinates

Tool: get_weather_by_location
Arguments: {"lat": 35.6812, "lon": 139.7671}

Get forecast for Tokyo

Tool: get_forecast
Arguments: {"prefecture": "tokyo"}

Get historical weather data

Tool: get_historical_weather
Arguments: {"station_code": "44132", "datetime": "2025-12-01 12:00"}

Get time series data (last 24 hours)

Tool: get_weather_time_series
Arguments: {"station_code": "44132", "hours": 24, "interval_minutes": 60}

Data Availability

Data Type Availability
Real-time observation ~30 min delay
Historical data Past 1-2 weeks
Time series Up to 168 hours (1 week)
Forecast 7 days ahead

License

MIT

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