refund_payment_order
AI agents use refund_payment_order to commit financial operations through Lfwin Payment — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly moves money by processing refunds, which commits financial obligations and has irreversible consequences (funds returned to customer). Financial category takes precedence over all others. Severity is critical due to high blast radius: an AI agent with unrestricted access could refund arbitrary amounts, drain accounts, or cause financial loss.
From the tool's definition Tool name 'refund_payment_order' on a payment capability service (lfwin-payment-mcp) explicitly designed to handle payment operations including 'initiating refunds'.
Attacks that exploit this kind of access
refund_payment_order. It is categorised as a Financial tool in the Lfwin Payment MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Lfwin Payment MCP server in PolicyLayer and add a rule for refund_payment_order: 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 Lfwin Payment. Nothing to install.
refund_payment_order 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_payment_order 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_payment_order. 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_payment_order is provided by the Lfwin Payment MCP server (litsen/lfwin-payment-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 →