Delete loose vertices and edges not connected to faces.
AI agents call delete_loose to permanently remove resources in BlenderMCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently deletes mesh components (vertices and edges) from a Blender scene without the ability to undo via the tool's parameters. While Blender has an undo system, the tool itself performs an irreversible deletion operation. The blast radius is high because an AI agent could accidentally remove significant portions of a user's 3D model if it misinterprets the geometry or context.
From the tool's definition 'Delete loose vertices and edges' — the tool irreversibly removes geometry from the 3D scene.
Attacks that exploit this kind of access
Delete loose vertices and edges not connected to faces. It is categorised as a Destructive tool in the BlenderMCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Blender MCP server in PolicyLayer and add a rule for delete_loose: 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 BlenderMCP. Nothing to install.
delete_loose 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_loose 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_loose. 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_loose is provided by the Blender MCP server (shirshovdim/retopoflow_blender_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →