Creates a refund for a specific application.\r\n \r\n\r\n<h4>Required permission(s):</h4><span class=
AI agents use create_applications_refunds to commit financial operations through Wpm Mcp Server — usually the final step of a payment, billing, or trading workflow. A call moves real money.
Refunds directly involve financial transactions by returning funds, making this a Financial category tool. Misuse could result in unauthorized or fraudulent refunds being issued, hence critical severity.
From the tool's definition Creates a refund for a specific application — issuing refunds is a financial operation that moves money back to applicants
Attacks that exploit this kind of access
Creates a refund for a specific application.\r\n \r\n\r\n<h4>Required permission(s):</h4><span class=. It is categorised as a Financial tool in the Wpm Mcp Server MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the Wpm Mcp Server MCP server in PolicyLayer and add a rule for create_applications_refunds: 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 Wpm Mcp Server. Nothing to install.
create_applications_refunds 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 create_applications_refunds 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 create_applications_refunds. 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.
create_applications_refunds is provided by the Wpm Mcp Server MCP server (wpm-mcp-server-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 →