AI agents use refund_purchase to commit financial operations through Hotmart — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly moves money back to customers by refunding purchases. Financial transactions are the most severe category and warrant critical severity due to the potential for unauthorized refunds, fraud, or large-scale financial loss if an AI agent misuses this capability without proper controls or authorization checks.
From the tool's definition Tool name 'refund_purchase' and description 'Refund a purchase' explicitly indicates movement of money. Server context confirms this is a digital products platform (Hotmart) where refunds represent financial transactions that reverse payments and commitments.
Attacks that exploit this kind of access
Refund a purchase. It is categorised as a Financial tool in the Hotmart MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Hotmart MCP server in PolicyLayer and add a rule for refund_purchase: 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 Hotmart. Nothing to install.
refund_purchase 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_purchase 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_purchase. 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_purchase is provided by the Hotmart MCP server (theyahia/hotmart-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 →