AI agents use update_submodel to create or update resources in Aas — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Aas environment.
The tool modifies data (updates a submodel) reversibly via the Eclipse BaSyx REST API. While the description is empty (lowering confidence slightly), the naming convention and server context make the intent clear. This is Write rather than Execute (no code/command execution), and not Destructive (updates are reversible).
From the tool's definition Tool name 'update_submodel' with empty description; server enables 'full CRUD operations on Asset Administration Shells, Submodels, and Submodel Elements.' Sibling tools include create_*, delete_*, and get_* operations, positioning this as a data modification…
Documented attack patterns abuse exactly the kind of access update_submodel 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 update_submodel:
{
"version": "1",
"default": "deny",
"tools": {
"update_submodel": {
"limits": [
{
"counter": "update_submodel_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_submodel stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
update_submodel. It is categorised as a Write tool in the Aas MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Aas MCP server in PolicyLayer and add a rule for update_submodel: 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.
update_submodel is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the update_submodel 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 update_submodel. 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.
update_submodel 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.