Search the US Coast Guard PSIX vessel registry by name (partial), call sign, official number, hull number (HIN), flag, service type, or build year. Returns vessels with USCG vessel id, name, call sign, service type, build year, status, official number, HIN, flag. Keyless, public-domain. US-flagge...
AI agents call maritime.vessel 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 queries a public-domain government registry and returns read-only vessel information. There are no side effects, no data modification, and the data is described as public-domain. The only concern is the pay-per-call financial model noted in the server description, but the tool itself is a pure read/search operation.
From the tool's definition Search the US Coast Guard PSIX vessel registry... Returns vessels with USCG vessel id, name, call sign, service type, build year, status, official number, HIN, flag. Keyless, public-domain.
Attacks that exploit this kind of access
Search the US Coast Guard PSIX vessel registry by name (partial), call sign, official number, hull number (HIN), flag, service type, or build year. Returns vessels with USCG vessel id, name, call sign, service type, build year, status, official number, HIN, flag. Keyless, public-domain. US-flagged vessels + foreign vessels with US PSC activity. Pair vesselId with maritime.cases. 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.vessel: 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.vessel 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.vessel 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.vessel. 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.vessel 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 →