delete_invoice_draft
AI agents call delete_invoice_draft to permanently remove resources in Mad Invoice — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Despite the empty description, the tool name unambiguously signals deletion of invoice draft records. Deletion is a destructive operation that cannot be undone. In a financial document management context, this poses a high blast radius if invoked unintentionally by an AI agent (e.g., deleting an invoice draft that was needed for compliance, audit, or customer records).
From the tool's definition Tool name is 'delete_invoice_draft' with an empty description. The verb 'delete' indicates irreversible removal of data.
Attacks that exploit this kind of access
delete_invoice_draft. It is categorised as a Destructive tool in the Mad Invoice MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Mad Invoice MCP server in PolicyLayer and add a rule for delete_invoice_draft: 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 Mad Invoice. Nothing to install.
delete_invoice_draft 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_invoice_draft 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_invoice_draft. 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_invoice_draft is provided by the Mad Invoice MCP server (mad-sol-dev/mad-invoice-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 →