Refund an order
AI agents use fcart_refund_order to commit financial operations through FluentCommunity Manager — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Refunding an order is a financial operation that commits financial obligations and reverses payment flows. This falls under the Financial category, the highest severity tier. Even though the blast radius depends on order selection logic, refunds are inherently financial transactions. High severity because a misused refund tool could result in unauthorized money transfers to customers or loss of revenue.
From the tool's definition Tool name 'fcart_refund_order' and description 'Refund an order' explicitly indicate refund operations, which move money back to customers.
Attacks that exploit this kind of access
Refund an order. It is categorised as a Financial tool in the FluentCommunity Manager MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the FluentCommunity Manager MCP server in PolicyLayer and add a rule for fcart_refund_order: 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 FluentCommunity Manager. Nothing to install.
fcart_refund_order 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 fcart_refund_order 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 fcart_refund_order. 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.
fcart_refund_order is provided by the FluentCommunity Manager MCP server (wplaunchify/fluent-community-mcp). 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 →