FEMA Public Assistance (PA) funded project details — the post-disaster grants FEMA obligates to state/local/tribal governments and eligible nonprofits to repair public infrastructure and cover emergency response (debris removal, roads, buildings, utilities). Filter by state (2-letter) and/or disa...
AI agents call gov.public-assistance 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 data retrieval tool that queries public FEMA disaster assistance records. It has no side effects—it neither modifies infrastructure data, executes operations, deletes records, nor moves funds. The financial amounts returned are informational context about obligated grants, not transactions initiated by the tool. The tool is read-only and poses minimal risk if called by an AI agent.
From the tool's definition Tool description indicates it 'returns' public assistance project details with filters and data retrieval only. No modifications, deletions, executions, or financial transactions are performed.
Attacks that exploit this kind of access
FEMA Public Assistance (PA) funded project details — the post-disaster grants FEMA obligates to state/local/tribal governments and eligible nonprofits to repair public infrastructure and cover emergency response (debris removal, roads, buildings, utilities). Filter by state (2-letter) and/or disasterNumber (one required); optionally refine by incidentType. Returns total matching worksheet count + projects (disaster number, declaration date, incident type, project worksheet number, applicant, damage category, project size, status, county, federal share obligated / total obligated / project amount USD, obligation date), largest federal share first. Free, public-domain (OpenFEMA). Distinct from gov.hazard-mitigation (future-risk grants) and gov.nfip-claims (flood losses) — disaster recovery funding for public infrastructure. 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.public-assistance: 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.public-assistance 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.public-assistance 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.public-assistance. 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.public-assistance 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 →