AI agents use createPixCharge to commit financial operations through Pix — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly creates payment charges, which constitutes a financial transaction or commitment. Even though it generates a QR code (static representation), the act of 'creating a charge' is a financial operation that moves or commits money. The potential for an AI agent to misuse this—generating charges without proper authorization or for incorrect amounts—represents a critical blast radius.
From the tool's definition Tool description states 'Create a new Pix payment charge' and server enables 'Brazilian payments'; Pix is Brazil's instant payment system; creating a charge commits a financial obligation.
Attacks that exploit this kind of access
Create a new Pix payment charge with QR code. It is categorised as a Financial tool in the Pix MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Pix MCP server in PolicyLayer and add a rule for createPixCharge: 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 Pix. Nothing to install.
createPixCharge 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 createPixCharge 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 createPixCharge. 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.
createPixCharge is provided by the Pix MCP server (regenerating-world/pix-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 →