Cancel a subscription
AI agents call cancel_subscription to permanently remove resources in Hotmart — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Subscription cancellations represent destructive operations because they permanently terminate ongoing agreements and revenue streams. While the action may theoretically be reversible through re-subscription, the tool itself offers no undo mechanism and the consequences (loss of service access, interruption of recurring billing) are material and lasting.
From the tool's definition cancel_subscription performs an irreversible cancellation of an active subscription, which terminates a recurring service agreement and cannot be undone without manual intervention or re-enrollment.
Attacks that exploit this kind of access
Cancel a subscription. It is categorised as a Destructive tool in the Hotmart MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Hotmart MCP server in PolicyLayer and add a rule for cancel_subscription: 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.
cancel_subscription is a Destructive 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 cancel_subscription 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 cancel_subscription. 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.
cancel_subscription 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 →