AI agents call customs_query_ship_plan to retrieve information from Customs without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves information about a ship's container plan—a read-only operation. It has no capacity to modify, delete, execute code, or create financial obligations. The blast radius of misuse is minimal, limited to potential information disclosure of shipping logistics data. Confidence is high given the explicit 'Get' verb and query nature of the operation.
From the tool's definition Tool name 'customs_query_ship_plan' and description 'Get the container ship plan associated with a transport vessel' indicate a retrieval operation with no modification or side effects.
Attacks that exploit this kind of access
Get the container ship plan associated with a transport vessel. It is categorised as a Read tool in the Customs MCP Server, which means it retrieves data without modifying state.
Register the Customs MCP server in PolicyLayer and add a rule for customs_query_ship_plan: 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 Customs. Nothing to install.
customs_query_ship_plan 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 customs_query_ship_plan 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 customs_query_ship_plan. 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.
customs_query_ship_plan is provided by the Customs MCP server (yak33/customs-mcp-server). 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 →