process_refund
AI agents use process_refund to commit financial operations through Qanat Goose MCP Extension — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Refunds constitute financial transactions that move money and create financial obligations. Even in a sandbox environment, the capability to process refunds is a financial operation with critical severity due to potential for misuse (unauthorized refunds, customer fraud, financial liability).
From the tool's definition Tool name 'process_refund' indicates movement of money back to customers; combined with Square sandbox integration context showing this is a payment/orders system
Attacks that exploit this kind of access
process_refund. It is categorised as a Financial tool in the Qanat Goose MCP Extension MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Qanat Goose MCP Extension MCP server in PolicyLayer and add a rule for process_refund: 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 Qanat Goose MCP Extension. Nothing to install.
process_refund 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 process_refund 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 process_refund. 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.
process_refund is provided by the Qanat Goose MCP Extension MCP server (professordnyc/qanat-goose-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 →