FEMA federal disaster & emergency declarations — every federally declared disaster since 1953, including ones declared this week. Filter by state (2-letter), disasterNumber, declarationType (DR=major disaster, EM=emergency, FM/FS/FW=fire management), incidentType (Hurricane, Fire, Flood, Severe S...
AI agents call gov.disaster-declarations to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a straightforward data retrieval tool that queries and filters a historical public database of federal disaster declarations. It has no side effects, cannot modify or delete data, and does not execute code or trigger external operations. The filtering parameters (state, disaster number, date range, etc.) are all input filters for read-only queries.
From the tool's definition Tool provides filtered queries of historical FEMA disaster declarations data since 1953. The description explicitly states it filters and returns records with no mention of modification, deletion, or execution capabilities.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
FEMA federal disaster & emergency declarations — every federally declared disaster since 1953, including ones declared this week. Filter by state (2-letter), disasterNumber, declarationType (DR=major disaster, EM=emergency, FM/FS/FW=fire management), incidentType (Hurricane, Fire, Flood, Severe Storm, …), county (5-digit FIPS), fiscal year (fyDeclared), and declaration date range (fromDate/toDate, YYYY-MM-DD). No filter → most recent declarations nationwide. Returns total matching count + records (one per designated county/area) with declaration string, disaster number, title, incident type, declaration/incident/closeout dates, designated area, county FIPS, FEMA region, and authorized assistance programs (Individuals & Households, Individual Assistance, Public Assistance, Hazard Mitigation). Free, public-domain (OpenFEMA). Distinct from gov.risk-index (modeled future risk) and gov.nfip-claims (realized flood losses) — the official federal-response record, for disaster logistics, eligibility checks, insurance, emergency management. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for gov.disaster-declarations: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp. Nothing to install.
gov.disaster-declarations is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the gov.disaster-declarations rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for gov.disaster-declarations. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
gov.disaster-declarations is provided by the MCP server (@2sio/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →