Arlet

Connect J-SHIS Seismic Hazard to ChatGPT

Query J-SHIS Seismic Hazard 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 J-SHIS (Japan Seismic Hazard Information Station) Web API, the official seismic hazard database operated by NIED, Japan's national disaster-resilience research institute. J-SHIS publishes the probabilistic seismic hazard maps produced by the government's Headquarters for Earthquake Research Promotion.

Key features:

  • Seismic hazard by location: pass latitude/longitude anywhere in Japan and get the 250m-mesh probability of experiencing JMA seismic intensity 5-lower, 5-upper, 6-lower, or 6-upper (or stronger) shaking within the next 30 years, plus the expected shaking at standard exceedance probabilities - reported as JMA intensity classes and peak ground velocities, not as raw codes.
  • Dominant earthquakes and faults: for a municipality (5-digit code), a prefecture (name or code) or a single point, get the ranked list of earthquakes and active faults that matter most there, with occurrence probability, magnitude and the population exposed to strong shaking. This works without any coordinates, so a place name is enough to get started.
  • Surface soil conditions: microtopography classification (reclaimed land, natural levee, volcanic ash upland, ...), AVS30 (average shear-wave velocity in the top 30m) with a plain-language ground-hardness class, and the ground-motion amplification factor.
  • Landslide topography: whether a point's 250m mesh intersects NIED's mapped landslide landforms, with a J-SHIS Map link.
  • Hazard curves: the full relationship between peak bedrock velocity and its 30/50-year exceedance probability, for quantitative risk analysis.

Typical uses: assessing earthquake risk of a home, office, or facility location; comparing candidate sites; disaster-preparedness reports. The API is public and free, so no API key or registration is required.

These values are probabilities from a long-term model, not predictions of when an earthquake will occur, and they are 250m-mesh averages that say nothing about a specific building. When you use the results, cite the source (J-SHIS, NIED). Bulk redistribution of the raw data as-is is not permitted by the terms of use.

How to connect J-SHIS Seismic Hazard to ChatGPT

  1. 1

    In the Arlet dashboard, open Data tools, find J-SHIS Seismic Hazard and switch it on. No API key setup is needed.

  2. 2

    In ChatGPT, open Settings β†’ Plugins β†’ Browse plugins and click + at the top right.

  3. 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. 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.

Use J-SHIS Seismic Hazard with other AI clients