AI agents use pay_x402 to commit financial operations through Cardzero — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly commits financial obligations by sending USDC payments to access HTTP resources. Even though amounts may be small or pre-authorized, the tool executes irreversible financial transactions. It is the most severe category (Financial > Destructive > Execute > Write > Read).
From the tool's definition 'Pay for an x402-protected HTTP resource' and 'send USDC payments' in server description; tool moves money (USDC) to access external resources; x402 is HTTP payment protocol standard
Attacks that exploit this kind of access
Pay for an x402-protected HTTP resource (HTTP 402 Payment Required). Use after receiving a 402 response. Returns a paymentHeader to include in the retry request as X-PAYMENT header. It is categorised as a Financial tool in the Cardzero MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Cardzero MCP server in PolicyLayer and add a rule for pay_x402: 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 Cardzero. Nothing to install.
pay_x402 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 pay_x402 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 pay_x402. 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.
pay_x402 is provided by the Cardzero MCP server (mrocker/cardzero-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 →