FEMA National Risk Index for a US county — the authoritative natural-hazard risk profile. Look up by countyFips (5-digit STCOFIPS), state + county name, or a lat/lon point. Returns the composite Risk Index score/rating/national-percentile (18-hazard model = Expected Annual Loss × Social Vulnerabi...
AI agents call gov.risk-index 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 tool retrieves and queries authoritative public hazard risk data indexed by location (FIPS code, county name, or coordinates). It performs a lookup operation with no side effects—no data creation, modification, deletion, code execution, or financial obligations. The tool is informational only, supporting decision-making for siting, insurance assessment, and planning.
From the tool's definition Tool description states it 'Look up' and 'Returns' data about FEMA National Risk Index scores, ratings, and hazard profiles. No modification, deletion, execution, financial transaction, or destructive capability described.
Attacks that exploit this kind of access
FEMA National Risk Index for a US county — the authoritative natural-hazard risk profile. Look up by countyFips (5-digit STCOFIPS), state + county name, or a lat/lon point. Returns the composite Risk Index score/rating/national-percentile (18-hazard model = Expected Annual Loss × Social Vulnerability ÷ Community Resilience), each component, and per-hazard risk ratings + expected annual loss for all 18 hazards (wildfire, earthquake, hurricane, riverine & coastal flooding, tornado, heat/cold wave, drought, …). Free, public-domain. For siting, insurance, and resilience planning; complements geo.flood-zone (flood SFHA only). 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.risk-index: 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.risk-index 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.risk-index 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.risk-index. 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.risk-index 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 →