Preview or complete a Costco order. Use confirm=false to preview first.
AI agents use checkout to commit financial operations through Mcp Costco — usually the final step of a payment, billing, or trading workflow. A call moves real money.
When confirm=true, this tool finalizes a purchase on Costco.com, charging the user's payment method. This constitutes a financial transaction. The blast radius is critical because an AI agent could inadvertently complete large orders without user intent. Confidence is slightly below 1.0 because the tool can also be used in preview mode (confirm=false), but the primary risk path is financial.
From the tool's definition 'complete a Costco order' and 'confirm=false to preview first' — the confirm=true path places a real purchase order, committing financial obligations
Attacks that exploit this kind of access
Preview or complete a Costco order. Use confirm=false to preview first. It is categorised as a Financial tool in the Mcp Costco MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Mcp Costco MCP server in PolicyLayer and add a rule for 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 Mcp Costco. Nothing to install.
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 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 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.
checkout is provided by the Mcp Costco MCP server (markswendsen-code/mcp-costco). 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 →