AI agents call get_submodel_refs to retrieve information from Aas without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'get_' prefix combined with 'submodel_refs' indicates this tool queries/retrieves submodel references from Asset Administration Shells. Retrieval operations have no side effects and fall into the Read category. Low severity because reading references poses minimal risk—blast radius is limited to information disclosure.
From the tool's definition Tool name 'get_submodel_refs' indicates retrieval of submodel references. The server description confirms CRUD operations are supported, and 'get_' prefix is a standard read operation pattern.
Documented attack patterns abuse exactly the kind of access get_submodel_refs 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 get_submodel_refs:
{
"version": "1",
"default": "deny",
"tools": {
"get_submodel_refs": {}
}
}get_submodel_refs is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
get_submodel_refs. It is categorised as a Read tool in the Aas MCP Server, which means it retrieves data without modifying state.
Register the Aas MCP server in PolicyLayer and add a rule for get_submodel_refs: 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.
get_submodel_refs 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 get_submodel_refs 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 get_submodel_refs. 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.
get_submodel_refs 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.