AI agents call get_submodels 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 and naming convention strongly suggest this retrieves Submodel data without modification. Despite the empty description, contextual evidence from the server's stated CRUD capability and consistent naming patterns across sibling tools supports classification as a Read operation with low severity (no side effects, only data retrieval).
From the tool's definition Tool name 'get_submodels' indicates a retrieval operation. The server description confirms it enables CRUD operations via REST API, and 'get_' prefix conventionally denotes read-only queries.
Documented attack patterns abuse exactly the kind of access get_submodels 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_submodels:
{
"version": "1",
"default": "deny",
"tools": {
"get_submodels": {}
}
}get_submodels 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_submodels. 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_submodels: 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_submodels 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_submodels 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_submodels. 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_submodels 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.