Skip to main content
Glama
sgarcese
by sgarcese

FEMA Data MCP

A read-only Model Context Protocol server that exposes nationwide FEMA data for building clear, location-aware household emergency preparedness plans.

The first release focuses on durable planning context rather than live incident response:

  • FEMA National Risk Index v1.20 hazard profiles at county or Census-tract level

  • OpenFEMA disaster declaration history by state or county

  • A combined community context packet for downstream planning applications

This server does not produce evacuation guidance, forecasts, property-level risk determinations, or real-time emergency alerts.

MCP tools

Tool

Purpose

get_hazard_profile

Rank FEMA's 18 natural hazards for a county or Census tract, including overall risk, social vulnerability, and community resilience.

list_disaster_declarations

Find FEMA declarations by state or county, date range, incident type, and declaration type.

get_community_context

Combine the hazard profile with recent county declaration history in one planning-oriented response.

Locations can be supplied as a 5-digit county FIPS, an 11-digit Census tract FIPS, or latitude/longitude. The MCP intentionally does not collect or geocode a street address. Coordinate queries are transmitted to FEMA's ArcGIS service; use a county or tract FIPS instead when precise coordinates are unnecessary.

Related MCP server: DeepMap AI MCP Server

Run locally

Requires Node.js 22 or newer.

npm install
cp .env.example .env
npm run check
npm run dev

Health check: GET http://localhost:3000/health

MCP endpoint: POST http://localhost:3000/mcp

To inspect the tools interactively:

npx @modelcontextprotocol/inspector

Choose Streamable HTTP and connect to http://localhost:3000/mcp.

Configuration

  • PORT — listening port; defaults to 3000.

  • ALLOWED_ORIGINS — comma-separated browser origins permitted to call /mcp. Requests without an Origin header, such as normal server-side MCP clients, remain supported.

No FEMA API key is required. Upstream requests have a 15-second timeout and all responses include source provenance and a safety caveat.

Data sources and scope

Risk scores are planning baselines, not predictions. A federal declaration is administrative and historical context, not evidence that an emergency is active. Any eventual planning product must pair these results with current instructions from local emergency management and alerting authorities.

See the architecture for boundaries and the planned data surface.

Development workflow

The project uses a test-first workflow, keeps changes reviewable, and deploys only through CI after merge. Canonical commands are:

npm test
npm run lint
npm run format:check
npm run typecheck
npm run build
npm run check

License

Released under the MIT License.

Related MCP Connectors

Related MCP Servers

  • A
    license
    A
    quality
    D
    maintenance
    ollect comprehensive environmental data from 80+ US federal sources (FEMA, EPA, USGS, NOAA, NRCS, USFWS, DOE, DOT, CDC, Census) for any US location. One tool returns flood zones, soils, wetlands, rainfall, water quality, contamination, seismic risk, infrastructure, ecology, energy, and demographics.
    3
    5 npm
    6
    MIT
  • A
    license
    Not graded
    quality
    D
    maintenance
    Provides 25 geophysical intelligence tools for multi-hazard risk scoring, earthquake/volcano/tsunami/sinkhole prediction, weather intelligence, insurance underwriting, climate migration, and parametric triggers.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables emergency medical coordination with tools for triage, medication guidance, blood donor outreach, mass casualty simulation, and emergency plan generation.
    MIT