Executes a previously drafted refund. SIMULATED — no real payment processor is called. Marks the order as refunded.
AI agents use execute_refund_order to commit financial operations through AgentBridge MCP Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Although the description notes the refund is SIMULATED and no real payment processor is called, the tool's core purpose is to execute financial refund operations. Even in a simulated environment, refunds represent financial commitments and state changes to orders. An AI agent misusing this tool could incorrectly process refunds for orders, causing financial discrepancies and operational disruption.
From the tool's definition Tool name is 'execute_refund_order' and description states it 'Executes a previously drafted refund' and 'Marks the order as refunded.' This directly involves processing refunds, which are financial transactions that commit financial obligations.
Attacks that exploit this kind of access
Executes a previously drafted refund. SIMULATED — no real payment processor is called. Marks the order as refunded. It is categorised as a Financial tool in the AgentBridge MCP Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the AgentBridge MCP Server MCP server in PolicyLayer and add a rule for execute_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 AgentBridge MCP Server. Nothing to install.
execute_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 execute_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 execute_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.
execute_refund_order is provided by the AgentBridge MCP Server MCP server (marmar9615-cloud/agentbridge-protocol). 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 →