Soft-delete a property. The property is hidden from queries but can be
AI agents call delete_property to permanently remove resources in REP Helper — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool removes properties from the rental hours tracking system used for IRS Real Estate Professional Status documentation. Deleting properties that are material to tax filings could result in loss of critical evidence for tax compliance, leading to incorrect tax reporting, audit failures, or financial penalties.
From the tool's definition Tool name is 'delete_property' and description states 'Soft-delete a property.' The verb 'delete' combined with removal from queries indicates irreversible data removal, even if technically recoverable as a soft-delete.
Attacks that exploit this kind of access
Soft-delete a property. The property is hidden from queries but can be. It is categorised as a Destructive tool in the REP Helper MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the REP Helper MCP server in PolicyLayer and add a rule for delete_property: 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 REP Helper. Nothing to install.
delete_property 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_property 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_property. 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_property is provided by the REP Helper MCP server (rephelper-ai/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 →