Delete an expense and all its splits.
AI agents call delete_expense to permanently remove resources in Expense — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes expense records and their associated split data, which cannot be undone. While not financial in the sense of moving money, it destroys financial ledger entries. This is a Destructive action (irreversible deletion) rather than Write (reversible modification). High severity because accidental deletion of expense records could corrupt financial tracking for users or shared groups.
From the tool's definition Tool name is 'delete_expense' and description states 'Delete an expense and all its splits.' The verb 'delete' combined with the scope 'and all its splits' indicates irreversible removal of data.
Attacks that exploit this kind of access
Delete an expense and all its splits. It is categorised as a Destructive tool in the Expense MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Expense MCP server in PolicyLayer and add a rule for delete_expense: 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 Expense. Nothing to install.
delete_expense 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_expense 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_expense. 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_expense is provided by the Expense MCP server (shivamprasad1001/expense-mcp-server). 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 →