AI agents call destroy_entity to permanently remove resources in Threlte — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes entities from a Three.js/Threlte scene. While the blast radius is confined to the 3D scene (not production data or financial systems), the operation is irreversible—a destroyed entity cannot be recovered without external undo mechanisms or backups. An AI agent with unchecked access could delete critical scene elements, breaking visualizations or interactive experiences.
From the tool's definition Tool name 'destroy_entity' and description 'Remove an entity from the scene' indicate irreversible deletion of scene objects. The verb 'destroy' and 'remove' are destructive operations that cannot be undone within the tool's interface.
Documented attack patterns abuse exactly the kind of access destroy_entity gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Threlte, and nothing reaches the server without passing your rules. This is the rule we recommend for destroy_entity:
{
"version": "1",
"default": "deny",
"hide": [
"destroy_entity"
]
}destroy_entity disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Remove an entity from the scene. It is categorised as a Destructive tool in the Threlte MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Threlte MCP server in PolicyLayer and add a rule for destroy_entity: 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 Threlte. Nothing to install.
destroy_entity is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the destroy_entity 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 destroy_entity. 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.
destroy_entity is provided by the Threlte MCP server (serifeusstudio/threlte-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Threlte, 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.
30 Threlte tools catalogued and risk-classified — across an index of 43,000+ MCP servers.