Japanese Weather

Provides weather forecasts and current conditions for 110 Japanese cities via MCP, supporting natural language queries and HTTP transport.

python

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "tsukiyama85-japanese-weather-mcp": {
      "command": "uv",
      "args": [
        "run",
        "-m",
        "src.japanese_weather_mcp.main"
      ],
      "env": {
        "MCP_HOST": "127.0.0.1",
        "MCP_PATH": "/mcp/",
        "MCP_PORT": "8000",
        "LOG_LEVEL": "INFO",
        "MCP_TRANSPORT": "streamable-http"
      }
    }
  }
}

This MCP server provides weather information for Japan through a FastMCP-based implementation. It supports natural language inputs, HTTP transport, and Docker-based deployment, enabling you to query weather data for 110 cities nationwide with easy-to-use clients.

How to use

You can run the weather MCP server locally and connect using an MCP client like Claude Desktop or Gemini in natural language mode. Start the server in stdio mode, then run the client to issue weather questions such as the current weather for a city, a multi-day forecast, or location-based searches. The server exposes tools that let you fetch weather data by location and date range and to search for locations by query.

Steps to use: 1) Start the MCP server in stdio mode with your preferred runtime. 2) Launch your MCP client and point it to the server. 3) Ask natural language questions using city names in Kanji, Hiragana, or Katakana. 4) Use the available tools to retrieve current weather, forecasts, or location search results.

How to install

Prerequisites: you need Python 3.10+ or the uv runtime (recommended) to run the MCP server, plus Docker if you want a Docker-based deployment.

Step-by-step commands to get up and running locally without Docker:

# Option A: Using uvx (recommended)
uv sync
uv run -m src.japanese_weather_mcp.main

# Option B: Using plain Python (pip)
python -m src.japanese_weather_mcp.main

Additional setup and notes

Configuration and environment variables control how the MCP server runs and how it is exposed to clients. The following environment variables configure transport, host, port, path, and logging. You can adjust these as needed for your deployment.

Environment variables you may set from your deployment environment include:

MCP_TRANSPORT: streamable-http (transport protocol) - MCP_HOST: 127.0.0.1 - MCP_PORT: 8000 - MCP_PATH: /mcp/ - LOG_LEVEL: INFO

HTTP API and local tools

While you can run the server locally, HTTP-based usage via a remote MCP endpoint is supported for clients that can talk over HTTP. The following tools are exposed by the server to fetch weather data in a structured way.

Troubleshooting notes

If you encounter connectivity issues, verify that the MCP server process is running and listening on the configured host and port. Check that the client is pointed to the correct path and port. Ensure the environment variables are set correctly for your deployment and that the chosen transport matches the client configuration.

Security considerations

Limit access to the MCP HTTP endpoint to trusted clients or networks. Apply standard security practices for your environment, including network restrictions and proper access controls for any API keys or credentials used by clients.

Examples of questions you can ask

Examples include:

東京の今日の天気は？
大阪の3日間の予報を教えて
札幌の現在の気温は？

Available tools

get_weather

Fetches a weather forecast for a given location and number of days (1-7)

get_current_weather

Retrieves current weather conditions for a specific location

search_locations

Searches for locations by a text query

Built by

VeilStrat

AI signals for GTM teams