FEMA National Flood Insurance Program (NFIP) claims history for a US location — the flood losses actually paid out in an area. Requires state (2-letter); narrow by county (5-digit FIPS), ZIP, and yearOfLoss range. Returns the total matching claim count plus recent redacted claims (date of loss, c...
AI agents call gov.nfip-claims 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 historical NFIP claims data from a public database. It performs no data modification, deletion, financial transfers, or code execution. The tool is purely informational, returning aggregated and individual claim records for research, analysis, or compliance purposes.
From the tool's definition Tool description states it 'Returns the total matching claim count plus recent redacted claims' with historical data retrieval. The action verbs are 'narrow', 'filter', and 'Returns' — all query/retrieval operations.
Attacks that exploit this kind of access
FEMA National Flood Insurance Program (NFIP) claims history for a US location — the flood losses actually paid out in an area. Requires state (2-letter); narrow by county (5-digit FIPS), ZIP, and yearOfLoss range. Returns the total matching claim count plus recent redacted claims (date of loss, county/census tract/ZIP, rated flood zone, cause, water depth, net building + contents payment USD, approx lat/lon), largest net payout first. FEMA redacts city, so filter by county/ZIP. Free, public-domain (OpenFEMA). Distinct from geo.flood-zone (current SFHA) and gov.risk-index (modeled future risk) — this is the realized loss track record, for underwriting + property diligence. 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.nfip-claims: 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.nfip-claims 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.nfip-claims 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.nfip-claims. 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.nfip-claims 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 →