AI agents use sanctions_screen to commit financial operations through CorteX402 — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Although the tool description is empty, the server context makes clear that every tool invocation on this server triggers an on-chain USDC payment settlement. The tool name 'sanctions_screen' suggests it is a data retrieval product (Read), but the payment-per-call mechanism means each invocation commits a financial transaction. Financial category takes precedence over Read per severity rules.
From the tool's definition Server description states 'Every call settles in USDC with an on-chain receipt' and lists 'sanctions screening' as one of the pay-per-call data products on Base mainnet.
Attacks that exploit this kind of access
sanctions_screen. It is categorised as a Financial tool in the CorteX402 MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the CorteX402 MCP server in PolicyLayer and add a rule for sanctions_screen: 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 CorteX402. Nothing to install.
sanctions_screen is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the sanctions_screen 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 sanctions_screen. 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.
sanctions_screen is provided by the CorteX402 MCP server (ooak21/cortex402-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 →