AI agents use update_shell 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.
This tool modifies existing Asset Administration Shell configurations reversibly. While the description is empty (reducing confidence slightly), the server's explicit CRUD mandate and sibling delete/create operations confirm this is a Write operation.
From the tool's definition Tool name 'update_shell' on a server that performs 'full CRUD operations' on 'Asset Administration Shells' via REST API. Server description explicitly mentions 'update' as part of CRUD. Empty tool description lowers precision, but context is clear.
Documented attack patterns abuse exactly the kind of access update_shell 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_shell:
{
"version": "1",
"default": "deny",
"tools": {
"update_shell": {
"limits": [
{
"counter": "update_shell_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}update_shell 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_shell. 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_shell: 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_shell 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_shell 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_shell. 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_shell 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.