FEMA Data MCP
Provides access to FEMA National Risk Index hazard layers hosted on ArcGIS, enabling county- and tract-level queries for hazard risk, expected annual loss, social vulnerability, and community resilience.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@FEMA Data MCPCompare the hazard profile and recent disaster declarations for Harris County, TX"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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 |
| Rank FEMA's 18 natural hazards for a county or Census tract, including overall risk, social vulnerability, and community resilience. |
| Find FEMA declarations by state or county, date range, incident type, and declaration type. |
| 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 devHealth check: GET http://localhost:3000/health
MCP endpoint: POST http://localhost:3000/mcp
To inspect the tools interactively:
npx @modelcontextprotocol/inspectorChoose Streamable HTTP and connect to http://localhost:3000/mcp.
Claude Desktop over stdio
Build the server before configuring Claude Desktop:
npm install
npm run buildAdd an entry like this to claude_desktop_config.json, replacing both paths
with absolute paths on your machine:
{
"mcpServers": {
"fema-data": {
"command": "/absolute/path/to/node",
"args": ["/absolute/path/to/FEMA_MCP/dist/stdio.js"]
}
}
}Claude Desktop launches this process itself, so do not run npm run dev at
the same time. The stdio and HTTP entry points expose the same FEMA tools.
Configuration
PORT— listening port; defaults to3000.ALLOWED_ORIGINS— comma-separated browser origins permitted to call/mcp. Requests without anOriginheader, 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
FEMA National Risk Index provides relative risk, expected annual loss, social vulnerability, and community resilience at county and Census-tract resolution.
OpenFEMA Disaster Declarations Summaries provides federal declarations beginning in 1953.
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 checknpm test never calls FEMA. npm run test:live runs opt-in contract tests
against both upstream sources. For the National Risk Index ArcGIS layers, it
checks that every requested field is published on each layer and makes real
county, tract, and coordinate lookups. For OpenFEMA Disaster Declarations
Summaries v2, it checks that every field the client selects is published and
that OpenFEMA hasn't announced a deprecation, then makes real state and county
queries. Run it after changing either client's field lists.
GitHub Actions runs npm run check on every pull request and push to main
(.github/workflows/ci.yml). main is protected: changes land only through
pull requests, the npm run check job must pass on a branch that is up to date
with main, review conversations must be resolved, and admins are not exempt. A separate nightly
workflow (.github/workflows/live-contract.yml, also manually dispatchable)
runs the live FEMA contract tests so upstream schema changes surface without
blocking pull requests.
Dependabot (.github/dependabot.yml) opens weekly update PRs for npm packages
and GitHub Actions. Minor and patch bumps are grouped and majors arrive
separately; every update goes through the same required npm run check gate.
Merged branches are deleted automatically.
License
Released under the MIT License.
This server cannot be deployed
Maintenance
Related MCP Connectors
Query FEMA disaster declarations, public assistance grants, housing aid, and NFIP claims.
Climate and disaster risk for any place: 7-day weather risk, hazards, climate profile, country risk.
Federal disaster declarations, emergencies, and assistance data
FEMA disasters, NOAA weather alerts, USGS earthquakes. 4 tools.
Related MCP Servers
- AlicenseAqualityDmaintenanceollect 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.312 npm7MIT

DeepMap AI MCP Serverofficial
AlicenseNot gradedqualityDmaintenanceProvides 25 geophysical intelligence tools for multi-hazard risk scoring, earthquake/volcano/tsunami/sinkhole prediction, weather intelligence, insurance underwriting, climate migration, and parametric triggers.MIT- FlicenseNot gradedqualityCmaintenanceProvides access to the Moody's RMS Location Intelligence API for property catastrophe risk analysis, with 114+ data product layers covering multiple perils and regions.-
- AlicenseNot gradedqualityBmaintenanceEnables emergency medical coordination with tools for triage, medication guidance, blood donor outreach, mass casualty simulation, and emergency plan generation.MIT