pay_checkout
Create a virtual card AND fill the checkout form in one call. The card number is sent directly to the browser extension — you never see it. Call detect_checkout first to verify a form is present. After this, tell the user to review and click the submit button.
This record as markdown: /tools/agentpay/pay-checkout.md
What pay_checkout does on Agentpay
AI agents use pay_checkout to commit financial operations through Agentpay, usually the final step of a payment, billing, or trading workflow. A call moves real money.
| Parameter | Type | Required | Description |
|---|---|---|---|
amount | number | Yes | Amount to fund the card (e.g. 29.00) |
context | string | — | Why you need this card (shown in approval notification) |
currency | string | — | Currency code (default: usd) |
Parameters from the server's own tool schema.
Why pay_checkout is rated Critical
This tool directly facilitates financial transactions by creating virtual payment cards and autonomously filling checkout forms, which constitutes a commitment of financial obligation. The automated checkout form completion represents a critical financial action that could result in unauthorized charges or commitments if misused by an AI agent.
From the tool's definition Tool description explicitly states it 'Create a virtual card AND fill the checkout form' and mentions 'The card number is sent directly to the browser extension', indicating this tool commits financial transactions by creating payment cards and automatically…
Attacks that exploit this kind of access
The rule that runs pay_checkout safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Agentpay, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For pay_checkout, this is the rule to start with:
Any call to pay_checkout is blocked until a human approves it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Agentpay, apply this rule, and every pay_checkout call is checked against it from then on.
Questions about pay_checkout
Create a virtual card AND fill the checkout form in one call. The card number is sent directly to the browser extension — you never see it. Call detect_checkout first to verify a form is present. After this, tell the user to review and click the submit button. It is categorised as a Financial tool in the Agentpay MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
pay_checkout accepts 3 parameters: amount, context, currency. Required: amount. The full parameter table on this page comes from the server's own tool schema.
Register the Agentpay MCP server in PolicyLayer and add a rule for pay_checkout: 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 Agentpay. Nothing to install.
pay_checkout 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_checkout 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_checkout. 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_checkout is provided by the Agentpay MCP server (agentpay-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Agentpay, and thousands of servers like it.
Across the catalogue