AI agents use refund to commit financial operations through Vnpay — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Refunds directly move money back to customers and reverse financial obligations. This is a core financial operation on a payment gateway. Misuse by an AI agent (e.g., refunding arbitrary transactions without authorization) could cause direct monetary loss. Financial operations take highest severity priority per classification rules.
From the tool's definition Tool is explicitly described as 'Refund a VNPay transaction' on a payment gateway server. The server context confirms it 'Supports payment URL generation, transaction queries, refunds, tokenized payments, and IPN verification.' Refunds move money by reversing…
Attacks that exploit this kind of access
Refund a VNPay transaction. It is categorised as a Financial tool in the Vnpay MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Vnpay MCP server in PolicyLayer and add a rule for refund: 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 Vnpay. Nothing to install.
refund 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 refund 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 refund. 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.
refund is provided by the Vnpay MCP server (theyahia/vnpay-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 →