US Coast Guard activity / port-state-control case history for a vessel, by USCG vessel id (from maritime.vessel). Returns cases newest-first with activity id, start date, type (Boarding, Inspection, Investigation…), and process status. Keyless, public-domain. The compliance/inspection record behi...
AI agents call maritime.cases 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 historical US Coast Guard inspection/case data for a vessel. It is a read-only query of public-domain government records with no side effects, writes, or financial implications. Misuse risk is minimal since the data is already public.
From the tool's definition Returns cases newest-first with activity id, start date, type (Boarding, Inspection, Investigation…), and process status. Keyless, public-domain.
Attacks that exploit this kind of access
US Coast Guard activity / port-state-control case history for a vessel, by USCG vessel id (from maritime.vessel). Returns cases newest-first with activity id, start date, type (Boarding, Inspection, Investigation…), and process status. Keyless, public-domain. The compliance/inspection record behind a vessel. 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 maritime.cases: 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.
maritime.cases 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 maritime.cases 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 maritime.cases. 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.
maritime.cases 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 →