Confirm a previously-created payment intent with a payment method. For card intents this triggers authorization; for APM intents this returns a next_action (redirect, QR, etc).
AI agents use confirm_payment_intent to commit financial operations through Mcp Ap2 — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly triggers a financial authorization on a payment intent. Confirming a payment intent commits financial obligations and initiates a charge against a payment method, making it a Financial category tool with critical severity due to the potential for unauthorized or erroneous charges.
From the tool's definition Confirm a previously-created payment intent with a payment method... triggers authorization
Documented attack patterns abuse exactly the kind of access confirm_payment_intent gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for confirm_payment_intent:
{
"version": "1",
"default": "deny",
"tools": {
"confirm_payment_intent": {
"deny_if": [
{
"conditions": [],
"on_deny": "Requires human approval."
}
]
}
}
} Any call to confirm_payment_intent is blocked until a human approves it. The rest of the server keeps working.
Free to start. No card required.
Confirm a previously-created payment intent with a payment method. For card intents this triggers authorization; for APM intents this returns a next_action (redirect, QR, etc). It is categorised as a Financial tool in the Mcp Ap2 MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for confirm_payment_intent: 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 Mcp Ap2. Nothing to install.
confirm_payment_intent 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 confirm_payment_intent 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 confirm_payment_intent. 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.
confirm_payment_intent is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Ap2, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
1300 Mcp Ap2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.