Skip to main content

DeepMap AI MCP Server - Real-time volcano monitoring, earthquake prediction, seismic risk, and geophysical intelligence for Claude and MCP-compatible LLMs

Project description

DeepMap AI MCP Server

Real-time volcano monitoring, earthquake prediction, and geophysical intelligence as a Model Context Protocol server. Gives Claude (and any MCP-compatible LLM) direct access to live volcanic risk scores, earthquake predictions, seismic risk assessments, tidal forcing analysis, flight disruption forecasts, tidal eruption windows, LiDAR fault detection, and travel advisories.

Install

pip install deepmap-mcp

Configure for Claude Desktop

Add the following to your claude_desktop_config.json:

{
  "mcpServers": {
    "deepmap": {
      "command": "python",
      "args": ["-m", "volcanosafe.mcp_server"],
      "env": {
        "DEEPMAP_API_URL": "https://api.volcanosafe.com",
        "DEEPMAP_API_KEY": "dm_live_..."
      }
    }
  }
}

Or run directly from the command line:

deepmap-mcp

Available Tools

Volcano Tools

Tool Description
volcano_risk Full real-time risk assessment with seismic data, tidal state, travel advisory, and flight impact
volcano_quick Low-latency risk score without live seismic fetch -- ideal for batch or insurance queries
volcano_flights Flight disruption risk for airports near a volcano
volcano_tidal_forecast Tidal eruption risk window forecast based on Mf tidal cycle analysis
volcano_advisory Plain-text travel advisory with insurance recommendation and monitoring agency status
volcano_list List all monitored volcanoes with names, countries, coordinates, and last eruption dates
volcano_batch Quick risk scores for multiple volcanoes at once (max 10 per request)

Earthquake Tools

Tool Description
predict_earthquake ML earthquake risk prediction for a region using GradientBoosting trained on real USGS data. Returns risk score, confidence, and contributing features
list_earthquake_regions List all supported earthquake monitoring regions with bounds, historical rate, and magnitude of completeness
assess_current_earthquakes Current global seismic risk assessment across all monitored regions using live USGS data
earthquake_alert_cycle Full alert cycle across all monitored regions with triggered alerts and recommended actions
predict_seismic_risk Seismic hazard risk score (0-10) for any lat/lon combining Vs30 site classification, liquefaction probability, and amplification factor
analyze_tidal_forcing Tidal stress forcing analysis on earthquake triggering using Schuster's test and Rayleigh statistics
detect_fault_scarps LiDAR/3DEP slope-break fault scarp detection with strike, dip direction, and length estimates

Supported Earthquake Regions

Region Key Name
ucerf3 Southern California (UCERF3)
new_madrid New Madrid Seismic Zone
cascadia Cascadia Subduction Zone
wasatch Wasatch Front (Utah)
oklahoma Oklahoma (Induced)
trans_mexico Trans-Mexican Volcanic Belt

Environment Variables

Variable Default Description
DEEPMAP_API_URL https://api.volcanosafe.com API base URL
DEEPMAP_API_KEY (empty) API key for authenticated access
VOLCANOSAFE_BASE_URL (fallback) Legacy env var, still supported
VOLCANOSAFE_API_KEY (fallback) Legacy env var, still supported

Documentation

Full API documentation: https://api.volcanosafe.com/docs

License

MIT

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

deepmap_mcp-0.2.0.tar.gz (16.0 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

deepmap_mcp-0.2.0-py3-none-any.whl (17.6 kB view details)

Uploaded Python 3

File details

Details for the file deepmap_mcp-0.2.0.tar.gz.

File metadata

  • Download URL: deepmap_mcp-0.2.0.tar.gz
  • Upload date:
  • Size: 16.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for deepmap_mcp-0.2.0.tar.gz
Algorithm Hash digest
SHA256 bd3984498fa04e54f3e52798ae73a396573867d9a548f235553d944c5ab61104
MD5 244cbe494f6526cefa121141828d9bea
BLAKE2b-256 d77d7be586869c0089a72d22edc7f45829be3bc963721feb8fad945242ef453b

See more details on using hashes here.

File details

Details for the file deepmap_mcp-0.2.0-py3-none-any.whl.

File metadata

  • Download URL: deepmap_mcp-0.2.0-py3-none-any.whl
  • Upload date:
  • Size: 17.6 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.14.3

File hashes

Hashes for deepmap_mcp-0.2.0-py3-none-any.whl
Algorithm Hash digest
SHA256 3137f6da048a322453f4734bb2b7a27ed947433b98490c48671c92cc504edcb7
MD5 10fe2f651b22bba0e3d806530747f033
BLAKE2b-256 3ee2292ac6bc791b8b0c066facf1bdf24d4866db3cd5252f56c3ddee4c5f897a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page