AI agents call customs_get_import_export_status 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 the current status of customs declarations or bills of lading. The verb 'track' and 'get' indicate a read-only operation that returns information about existing trade documents without creating, modifying, deleting, or executing any actions. It has no blast radius for an AI agent misuse as it only exposes read access to status data.
From the tool's definition Tool name includes 'get' and description states 'Track the import/export flow status' — retrieves status information without modifying data or triggering side effects.
Attacks that exploit this kind of access
Track the import/export flow status of a declaration or bill of lading. 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_get_import_export_status: 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_get_import_export_status 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_get_import_export_status 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_get_import_export_status. 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_get_import_export_status 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 →