disaster_recovery_profile
One-call disaster-history and recovery read for a US area (county or place), keyed by NAME + state - distinct from location_risk_report, which scores a single site by address/lat-lon. Joins FEMA's OpenFEMA disaster declarations (the area's federally-declared disaster history: incident types, freq...
This record as markdown: /tools/io-github-blackboxfoundry-livedatalink/disaster-recovery-profile.md
What disaster_recovery_profile does on Livedatalink
AI agents call disaster_recovery_profile to retrieve information from Livedatalink without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
area | string | Yes | County or place name to profile (e.g. 'Harris', 'Orleans', 'New Orleans'). Use the name without the word 'County'. |
state | string | — | 2-letter US state code (or full state name) to scope the FEMA history (e.g. 'TX', 'LA'). Strongly recommended - required for an accurate county read. |
county | string | — | Alias for area; either may be supplied. |
address | string | — | Optional street address to attach a sample parcel/property record (Maryland statewide or Texas-Harris County only). |
Parameters from the server's own tool schema.
Why disaster_recovery_profile is rated Low
Even though disaster_recovery_profile only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs disaster_recovery_profile safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Livedatalink, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For disaster_recovery_profile, this is the rule to start with:
disaster_recovery_profile is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Livedatalink, apply this rule, and every disaster_recovery_profile call is checked against it from then on.
Questions about disaster_recovery_profile
One-call disaster-history and recovery read for a US area (county or place), keyed by NAME + state - distinct from location_risk_report, which scores a single site by address/lat-lon. Joins FEMA's OpenFEMA disaster declarations (the area's federally-declared disaster history: incident types, frequency, most-recent event, and the federal-assistance signal - which programs, Individual Assistance / Individuals & Households / Public Assistance / Hazard Mitigation, were authorized) with optional US Census ACS county population for exposure context (keyed off the FIPS codes the FEMA records carry; needs a Census key and degrades gracefully) and an optional best-effort parcel record for property context when an address is given (Maryland statewide / Texas-Harris County only). Returns a readable profile with a headline banding the area's disaster exposure LOW / MODERATE / HIGH from the declaration record. The FEMA leg is keyless and is the core signal; a source that fails is noted, not fatal. INFORMATIONAL public-record synthesis, NOT an insurance rating, a property flood-risk score, or a professional risk assessment. It is categorised as a Read tool in the Livedatalink MCP Server, which means it retrieves data without modifying state.
disaster_recovery_profile accepts 4 parameters: area, state, county, address. Required: area. The full parameter table on this page comes from the server's own tool schema.
Register the Livedatalink MCP server in PolicyLayer and add a rule for disaster_recovery_profile: 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 Livedatalink. Nothing to install.
disaster_recovery_profile 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 disaster_recovery_profile 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 disaster_recovery_profile. 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.
disaster_recovery_profile is provided by the Livedatalink MCP server (https://livedatalink.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Livedatalink, and thousands of servers like it.
This server
Across the catalogue