AI agents call delete_world to permanently remove resources in Worldlabs — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool deletes a world resource, which cannot be undone. This is a destructive operation affecting generated 3D world assets. While the blast radius depends on whether worlds are backups or critical, the irreversible nature of deletion makes this Destructive rather than Write. Severity is high because deleting entire worlds could disrupt applications or workflows, though it is not Financial.
From the tool's definition Tool name is 'delete_world' with no description provided. The verb 'delete' unambiguously indicates irreversible removal of data (a world asset).
Documented attack patterns abuse exactly the kind of access delete_world gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Worldlabs, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_world:
{
"version": "1",
"default": "deny",
"hide": [
"delete_world"
]
}delete_world 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.
delete_world. It is categorised as a Destructive tool in the Worldlabs MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Worldlabs MCP server in PolicyLayer and add a rule for delete_world: 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 Worldlabs. Nothing to install.
delete_world 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 delete_world 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 delete_world. 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.
delete_world is provided by the Worldlabs MCP server (sandraschi/worldlabs-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Worldlabs, 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.
20 Worldlabs tools catalogued and risk-classified — across an index of 43,000+ MCP servers.