Delete one object via ModelAdmin.delete_model(). Cascade behaviour is owned
AI agents call admin.destroy to permanently remove resources in Django Admin Mcp Api — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes data objects from the database. Even though cascade behavior is "owned" (meaning it respects Django's cascade rules), the operation cannot be undone and may affect related records. This makes it Destructive rather than Execute.
From the tool's definition Tool name is "admin.destroy" and description explicitly states "Delete one object via ModelAdmin.delete_model()" with cascade behavior. The verb "Delete" and method name "delete_model()" unambiguously indicate irreversible data removal.
Attacks that exploit this kind of access
Delete one object via ModelAdmin.delete_model(). Cascade behaviour is owned. It is categorised as a Destructive tool in the Django Admin Mcp Api MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Django Admin Mcp Api MCP server in PolicyLayer and add a rule for admin.destroy: 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 Django Admin Mcp Api. Nothing to install.
admin.destroy 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 admin.destroy 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 admin.destroy. 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.
admin.destroy is provided by the Django Admin Mcp Api MCP server (martincastroalvarez/django-admin-mcp-api). 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 →