Connect Public Research (Japan) to ChatGPT
Query Public Research (Japan) directly from ChatGPT. Arlet links the two through one MCP connection and takes care of API keys.
An index of reports and announcements published by public institutions of Japan (#1258), built from their official feeds. Nothing is stored server-side (fetched on call, short-lived memory cache only).
Cards are split by which institution published a report: this card carries only public institutions of Japan; other countries' institutions live on their own cards.
Tools:
- search_japan_public_reports: keyword search (omit query for newest first).
- fetch_report_content: always returns available=false plus the official URL (metadata-only index).
Institutions covered (7; feeds and each institution's terms of use verified against primary sources on 2026-08-12):
- Cabinet Office of Japan (cao.go.jp, id: jp-cao) - 公共データ利用規約 (第1.0版) / PDL 1.0 (CC BY 4.0 compatible)
- Ministry of Internal Affairs and Communications (soumu.go.jp, id: jp-soumu) - 公共データ利用規約 (第1.0版) / PDL 1.0 (CC BY 4.0 compatible)
- Ministry of Economy, Trade and Industry (meti.go.jp, id: jp-meti) - 公共データ利用規約 (第1.0版) / PDL 1.0 (CC BY 4.0 compatible)
- Ministry of Health, Labour and Welfare (mhlw.go.jp, id: jp-mhlw) - 公共データ利用規約 (第1.0版) / PDL 1.0 (CC BY 4.0 compatible)
- Ministry of Land, Infrastructure, Transport and Tourism (mlit.go.jp, id: jp-mlit) - 公共データ利用規約 (第1.0版) / PDL 1.0 (CC BY 4.0 compatible)
- Financial Services Agency (fsa.go.jp, id: jp-fsa) - 公共データ利用規約 (第1.0版) / PDL 1.0 (CC BY 4.0 compatible)
- Bank of Japan (boj.or.jp, id: jp-boj) - Non-commercial reproduction permitted with the source indicated; commercial reproduction requires prior consultation (Bank of Japan) (title and link only, no description shown)
Per-record `license` and `tos_url` carry the reuse terms. Where an institution requires permission for reproduction or commercial use, the official description is withheld and only title, date and URL are returned.
How to connect Public Research (Japan) to ChatGPT
- 1
In the Arlet dashboard, open Data tools, find Public Research (Japan) and switch it on. No API key setup is needed.
- 2
In ChatGPT, open Settings → Plugins → 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 → Security and login.