Delete object from Blender scene by name. Permanently removes object and its data. Cannot be undone via MCP. Args: - object_name (string): Object to delete Returns: Success confirmation Use when: Cleaning up scene, removing unwanted objects Don
AI agents call blender_delete_object to permanently remove resources in ClaudeKit Blender MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool irreversibly deletes Blender objects and associated data without the possibility of recovery through the MCP interface. While confined to the Blender application scope, the permanent and non-recoverable nature of the action makes it Destructive rather than Write.
From the tool's definition Tool description explicitly states 'Permanently removes object and its data. Cannot be undone via MCP.' The word 'delete' in the tool name combined with 'Cannot be undone' confirms irreversible deletion of scene data.
Attacks that exploit this kind of access
Delete object from Blender scene by name. Permanently removes object and its data. Cannot be undone via MCP. Args: - object_name (string): Object to delete Returns: Success confirmation Use when: Cleaning up scene, removing unwanted objects Don. It is categorised as a Destructive tool in the ClaudeKit Blender MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the ClaudeKit Blender MCP server in PolicyLayer and add a rule for blender_delete_object: 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 ClaudeKit Blender MCP. Nothing to install.
blender_delete_object 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 blender_delete_object 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 blender_delete_object. 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.
blender_delete_object is provided by the ClaudeKit Blender MCP server (olbboy/claudekit-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 →