Connect WBGT Heat Index to ChatGPT
Query WBGT Heat Index directly from ChatGPT. Arlet links the two through one MCP connection and takes care of API keys.
This server connects your AI client to the CSV data service of the Ministry of the Environment's heat illness prevention information site (netchusho yobo joho site), the official source of Japan's WBGT (wet-bulb globe temperature) heat index.
Key features:
- Resolve a place to one of the 841 active monitoring stations by place name, kana reading, romaji, prefecture, or address - or by latitude/longitude, which returns the nearest stations with their distance in km. (Stations are weather-station sites, so district-level names like Shibuya are not stations; coordinates or the prefecture view cover that case.)
- Get hourly observed WBGT values for the current month and a 3-day forecast in 3-hour steps for a station, each converted to the official heat-risk rank (danger 31+, severe warning 28-31, warning 25-28, caution 21-25, almost safe below 21). A `today` summary combines today's observed maximum with the remaining forecast so a single call answers 'is it dangerous there today', with the recommended action attached.
- Get today's heat index for every station in a prefecture in one call, ranked hottest first - useful for 'where is it hottest in Tokyo right now'.
- Check the heat stroke alert (netchusho keikai alert) and special alert bulletins issued 4 times a day (05/10/14/17 JST): a nationwide summary of regions under alert, or per-prefecture details including each station's forecast daily-max WBGT. Status flags are returned in plain words, with a legend explaining how the ordinary alert (WBGT 33+ somewhere in the region) differs from the special alert (WBGT 35+ at every station in the prefecture).
All timestamps are Japan Standard Time (UTC+9), and the upstream convention of writing midnight as 24:00 is preserved and explained in each response.
Important: the data service operates only during the hot season, roughly late April to late October each year (for FY2026: April 22 to October 21), and only the current season is served - there is no access to previous years. Outside this period the upstream files do not exist and tools return a clear seasonal notice instead of data.
The data is published free of charge with no API key or registration. Per the site's terms of use, output includes the attribution to the Ministry of the Environment.
How to connect WBGT Heat Index to ChatGPT
- 1
In the Arlet dashboard, open Data tools, find WBGT Heat Index and switch it on. No API key setup is needed.
- 2
In ChatGPT, open Settings β Plugins β Browse plugins and click + at the top right.
- 3
In the New Plugin form, enter "Arlet" as the Name, choose Server URL for Connection and enter https://mcp.arlet.dev/mcp/, pick OAuth for Authentication, check the risk acknowledgement and click Create.
- 4
Open the Arlet plugin you created, click Sign in with Arlet, sign in with Google and click Allow. The connection is complete.
If the Plugins screen is not shown, turn on Developer mode under Settings β Security and login.
