Charge an invoice (card/online payment). POST /invoices/{invoiceId}/charge. AMOUNT IN CENTS: e.g. 5500 = $55.00. Required: invoiceId, amount (integer cents), paymentType (offlinePaymentProvider | thirdPartyPaymentProvider | walletPaymentProvider | otherPayment). Use thirdPartyPaymentProvider for ...
AI agents use charge_invoice to commit financial operations through Rebillia MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool executes financial transactions that debit customer accounts and transfer money to the merchant. Even if the invoice already exists, the act of charging it moves actual funds, making it a Financial category tool. The critical severity reflects the direct ability to extract money from customers, with potential for significant unauthorized charges if misused by a compromised AI agent.
From the tool's definition Tool directly charges an invoice by moving money through payment providers. Description explicitly states 'Charge an invoice (card/online payment)' and requires parameters for amount in cents and payment type.
Attacks that exploit this kind of access
Charge an invoice (card/online payment). POST /invoices/{invoiceId}/charge. AMOUNT IN CENTS: e.g. 5500 = $55.00. Required: invoiceId, amount (integer cents), paymentType (offlinePaymentProvider | thirdPartyPaymentProvider | walletPaymentProvider | otherPayment). Use thirdPartyPaymentProvider for card/online. It is categorised as a Financial tool in the Rebillia MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Rebillia MCP Server MCP server in PolicyLayer and add a rule for charge_invoice: 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 Rebillia MCP Server. Nothing to install.
charge_invoice 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 charge_invoice 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 charge_invoice. 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.
charge_invoice is provided by the Rebillia MCP Server MCP server (rhinosaas/rebillia-mcp-server). 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 →