Select all Verse device actors of a given class name substring.
AI agents call device_select_by_class to retrieve information from Uefn without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Selecting actors in the editor is a read/query operation with no persistent side effects. It changes the editor selection state temporarily but does not modify, create, or delete any data. Misuse has minimal blast radius.
From the tool's definition "Select all Verse device actors of a given class name substring" — this is a selection/query operation that identifies actors matching a class name
Documented attack patterns abuse exactly the kind of access device_select_by_class gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Uefn, and nothing reaches the server without passing your rules. This is the rule we recommend for device_select_by_class:
{
"version": "1",
"default": "deny",
"tools": {
"device_select_by_class": {}
}
}device_select_by_class 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.
Select all Verse device actors of a given class name substring. It is categorised as a Read tool in the Uefn MCP Server, which means it retrieves data without modifying state.
Register the Uefn MCP server in PolicyLayer and add a rule for device_select_by_class: 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 Uefn. Nothing to install.
device_select_by_class 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 device_select_by_class 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 device_select_by_class. 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.
device_select_by_class is provided by the Uefn MCP server (quangdang46/uefn-verse-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Uefn, 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.
143 Uefn tools catalogued and risk-classified — across an index of 43,000+ MCP servers.