AI agents use create_refund to commit financial operations through Paymongo — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Refunds constitute financial operations that commit money transfers. While not necessarily causing net loss (reversing prior payments), they involve movement of funds and carry high blast radius if misused by an AI agent—e.g., refunding legitimate payments, refunding without proper authorization, or bulk refund abuse. This is unambiguously Financial rather than merely Write or Destructive.
From the tool's definition Tool explicitly 'moves money back to the customer' which is a financial transaction involving the reversal of payments. PayMongo is a payment gateway and this tool directly performs refunds.
Attacks that exploit this kind of access
Refund a payment, fully or partially (moves money back to the customer). It is categorised as a Financial tool in the Paymongo MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Paymongo MCP server in PolicyLayer and add a rule for create_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 Paymongo. Nothing to install.
create_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 create_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 create_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.
create_refund is provided by the Paymongo MCP server (theyahia/paymongo-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 →