Create a new empty CLO3D project, clearing the current scene.
AI agents call new_project to permanently remove resources in CLO3D MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
While the action creates something new, the destructive aspect is that it clears the current scene, which cannot be undone if the current project has unsaved changes. This is an irreversible operation on existing work, making Destructive the appropriate category over Write.
From the tool's definition 'clearing the current scene' — creating a new project irreversibly destroys the current unsaved scene state
Documented attack patterns abuse exactly the kind of access new_project gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CLO3D MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for new_project:
{
"version": "1",
"default": "deny",
"hide": [
"new_project"
]
} new_project 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.
Create a new empty CLO3D project, clearing the current scene. It is categorised as a Destructive tool in the CLO3D MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the CLO3D MCP Server MCP server in PolicyLayer and add a rule for new_project: 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 CLO3D MCP Server. Nothing to install.
new_project 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 new_project 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 new_project. 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.
new_project is provided by the CLO3D MCP Server MCP server (ubani-studio/clo3d-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CLO3D MCP Server, 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.
33 CLO3D MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.