Preview the cascade / protected impact of deleting one object before
AI agents call admin.delete_preview to retrieve information from Django Admin Mcp Api without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool only previews what would happen if a deletion were performed (showing cascade and protected relationships), without actually deleting anything. This is a Read operation. However, severity is medium because it reveals potentially sensitive structural and data information about related objects, and its presence alongside a sibling 'admin.destroy' tool suggests it's a precursor to destructive action.
From the tool's definition 'Preview the cascade / protected impact of deleting one object before' — this is a preview/read operation, not an actual delete
Attacks that exploit this kind of access
Preview the cascade / protected impact of deleting one object before. It is categorised as a Read tool in the Django Admin Mcp Api MCP Server, which means it retrieves data without modifying state.
Register the Django Admin Mcp Api MCP server in PolicyLayer and add a rule for admin.delete_preview: 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.delete_preview is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the admin.delete_preview 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.delete_preview. 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.delete_preview 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 →