Cancela/estorna uma charge.
AI agents use pagarme_cancel_charge to commit financial operations through Payments MCP — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool performs a financial operation that reverses or cancels a payment charge. While technically reversible (unlike destructive operations), it directly affects monetary obligations and customer billing. Financial operations are classified as the most severe category per the rules.
From the tool's definition Tool name 'pagarme_cancel_charge' combined with description 'Cancela/estorna uma charge' (Portuguese: 'Cancels/reverses a charge') on a payment gateway integration server. This directly manipulates financial transactions by reversing/canceling charges.
Attacks that exploit this kind of access
Cancela/estorna uma charge. It is categorised as a Financial tool in the Payments MCP MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Payments MCP server in PolicyLayer and add a rule for pagarme_cancel_charge: 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 Payments MCP. Nothing to install.
pagarme_cancel_charge 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 pagarme_cancel_charge 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 pagarme_cancel_charge. 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.
pagarme_cancel_charge is provided by the Payments MCP server (lpillonwp/mcp-payments). 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 →