AI agents call delete_submodel_ref to permanently remove resources in Aas — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool deletes submodel references, which irreversibly removes data relationships within Asset Administration Shell structures. While the tool description is empty, the explicit 'delete' verb combined with the server's CRUD context and related destructive sibling tools (delete_shell, delete_submodel, delete_submodel_element) makes the destructive nature clear.
From the tool's definition Tool name 'delete_submodel_ref' contains 'delete', indicating irreversible data removal. Server description confirms 'full CRUD operations' and the sibling tools include delete_shell, delete_submodel, and delete_submodel_element, establishing the delete…
Documented attack patterns abuse exactly the kind of access delete_submodel_ref gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Aas, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_submodel_ref:
{
"version": "1",
"default": "deny",
"hide": [
"delete_submodel_ref"
]
}delete_submodel_ref 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.
delete_submodel_ref. It is categorised as a Destructive tool in the Aas MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Aas MCP server in PolicyLayer and add a rule for delete_submodel_ref: 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 Aas. Nothing to install.
delete_submodel_ref 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_submodel_ref 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_submodel_ref. 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_submodel_ref is provided by the Aas MCP server (smartfactory-kl/aas-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Aas, 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.
25 Aas tools catalogued and risk-classified — across an index of 43,000+ MCP servers.