Delete a notification by ID.
AI agents call delete_notification to permanently remove resources in Payoza MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes notification records. Although notifications are typically lower-value data compared to financial records or payment links, deletion is inherently destructive and irreversible. In a payments context, notifications often track important transaction alerts, confirmations, and audit trails.
From the tool's definition Tool is named 'delete_notification' and explicitly performs deletion ('Delete a notification by ID'). Deletion operations are irreversible and cannot be undone.
Attacks that exploit this kind of access
Delete a notification by ID. It is categorised as a Destructive tool in the Payoza MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Payoza MCP Server MCP server in PolicyLayer and add a rule for delete_notification: 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 Payoza MCP Server. Nothing to install.
delete_notification is a Destructive 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 delete_notification 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 delete_notification. 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.
delete_notification is provided by the Payoza MCP Server MCP server (payoza/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 →