AI agents call customs_query_tariff 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 retrieves tariff data based on product identifiers. It queries existing information without creating, modifying, deleting, or executing any operations. The lookup has no side effects and poses minimal risk if misused by an AI agent—the worst outcome would be retrieving incorrect tariff information for reference purposes.
From the tool's definition Tool name 'customs_query_tariff' and description 'Look up tariff information by HS code or product name' indicate a read-only lookup operation with no modification or execution of external systems.
Attacks that exploit this kind of access
Look up tariff information by HS code (商品编号) or product name. 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_tariff: 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_tariff 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_tariff 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_tariff. 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_tariff 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 →