Confirm (accept) a buyer-initiated return request by return_sn.
AI agents use confirm_return to commit financial operations through Mcp Ap2 — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Accepting a return request initiates a financial reversal process (return of goods and/or funds), which commits a financial obligation. This is part of a payment/commerce protocol (AP2 - Agent-to-Agent Payment Protocol) and accepting returns directly impacts financial transactions, making it a Financial category action with high severity due to potential for misuse triggering unintended refunds or returns.
From the tool's definition Confirm (accept) a buyer-initiated return request by return_sn
Documented attack patterns abuse exactly the kind of access confirm_return 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_return:
{
"version": "1",
"default": "deny",
"tools": {
"confirm_return": {
"deny_if": [
{
"conditions": [],
"on_deny": "Requires human approval."
}
]
}
}
} Any call to confirm_return is blocked until a human approves it. The rest of the server keeps working.
Free to start. No card required.
Confirm (accept) a buyer-initiated return request by return_sn. 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_return: 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_return 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_return 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_return. 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_return 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.