Checkout with the current cart and complete the purchase -
AI agents use perform-purchase to commit financial operations through Shopping MCP Server (Amazon + Target) — usually the final step of a payment, billing, or trading workflow. A call moves real money.
This tool directly completes a financial transaction by placing a real order, committing monetary obligations on behalf of the user. It is the highest severity category (Financial) as misuse could result in unauthorized purchases charged to the user's account, and the action is not easily reversible once an order is placed.
From the tool's definition "Checkout with the current cart and complete the purchase"
Attacks that exploit this kind of access
Checkout with the current cart and complete the purchase -. It is categorised as a Financial tool in the Shopping MCP Server (Amazon + Target) MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Shopping MCP Server (Amazon + Target) MCP server in PolicyLayer and add a rule for perform-purchase: 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 Shopping MCP Server (Amazon + Target). Nothing to install.
perform-purchase 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 perform-purchase 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 perform-purchase. 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.
perform-purchase is provided by the Shopping MCP Server (Amazon + Target) MCP server (sachinparyani/mcp-server-shopping). 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 →