AI agents use send_payment 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 moves USDC cryptocurrency funds to an arbitrary Ethereum address, constituting a real financial transaction. It also incurs a 2% service fee, compounding the financial impact. Misuse by an AI agent could result in irreversible loss of funds to unintended recipients at any scale, making this critical severity.
From the tool's definition Send a USDC payment to any Ethereum address. A 2% service fee is deducted automatically from your wallet.
Attacks that exploit this kind of access
Send a USDC payment to any Ethereum address. A 2% service fee is deducted automatically from your wallet. Confirm amount and recipient with the user before calling. 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 send_payment: 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.
send_payment 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 send_payment 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 send_payment. 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.
send_payment 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 →