Securely delete tax return data after filing. This is irreversible.
AI agents call crow_tax_purge_return to permanently remove resources in Crow — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes sensitive financial data (tax returns). Destructive category applies because the action cannot be undone. Severity is high due to the sensitive nature of tax documents and the potential for data loss if triggered inappropriately; it is not critical since it targets a specific data type rather than system-wide infrastructure, and the action requires intentional invocation rather than…
From the tool's definition Tool description states 'Securely delete tax return data after filing' and explicitly notes 'This is irreversible.' The verb 'purge' in the tool name combined with 'delete' and 'irreversible' in the description clearly indicate permanent, non-recoverable data…
Documented attack patterns abuse exactly the kind of access crow_tax_purge_return gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for crow_tax_purge_return:
{
"version": "1",
"default": "deny",
"hide": [
"crow_tax_purge_return"
]
} crow_tax_purge_return disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Securely delete tax return data after filing. This is irreversible. It is categorised as a Destructive tool in the Crow MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Crow MCP server in PolicyLayer and add a rule for crow_tax_purge_return: 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 Crow. Nothing to install.
crow_tax_purge_return 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 crow_tax_purge_return 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 crow_tax_purge_return. 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.
crow_tax_purge_return is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crow, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.