# delete_object

Delete an object from the scene

Agent View of the PolicyLayer registry record for `delete_object`. HTML page: https://policylayer.com/tools/aryeon0228-blendermcp/delete-object

## Facts

- Tool: `delete_object`
- Server: BlenderMCP (`aryeon0228/blendermcp`) — https://policylayer.com/tools/aryeon0228-blendermcp.md
- Homepage: https://github.com/Aryeon0228/BlenderMCP
- Risk category: Destructive (Critical risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Hidden

## Example call (MCP tools/call, JSON-RPC 2.0)

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "delete_object",
    "arguments": {}
  }
}
```

## Why delete_object is rated Critical

Deletion of scene objects in Blender cannot be undone by the tool itself (undo would require separate action). While the blast radius is limited to a single 3D project file rather than critical infrastructure, the action is irreversible and destructive in nature. An AI agent could accidentally or maliciously remove important 3D assets, requiring manual restoration.

From the tool's own definition: "Tool name is 'delete_object' and description states 'Delete an object from the scene' — the verb 'delete' combined with removal from a scene constitutes irreversible data destruction."

## Use case

AI agents call delete_object 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.

## Recommended policy (PolicyLayer)

Verdict: **Hidden**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches BlenderMCP:

```json
{
  "version": "1",
  "default": "deny",
  "hide": [
    "delete_object"
  ]
}
```

## Other tools on BlenderMCP (11)

- `execute_blender_code` — Execute — https://policylayer.com/tools/aryeon0228-blendermcp/execute-blender-code.md
- `render_scene` — Execute — https://policylayer.com/tools/aryeon0228-blendermcp/render-scene.md
- `scale_object` — Execute — https://policylayer.com/tools/aryeon0228-blendermcp/scale-object.md
- `get_object_info` — Read — https://policylayer.com/tools/aryeon0228-blendermcp/get-object-info.md
- `get_scene_info` — Read — https://policylayer.com/tools/aryeon0228-blendermcp/get-scene-info.md
- `get_viewport_screenshot` — Read — https://policylayer.com/tools/aryeon0228-blendermcp/get-viewport-screenshot.md
- `create_object` — Write — https://policylayer.com/tools/aryeon0228-blendermcp/create-object.md
- `move_object` — Write — https://policylayer.com/tools/aryeon0228-blendermcp/move-object.md
- `rotate_object` — Write — https://policylayer.com/tools/aryeon0228-blendermcp/rotate-object.md
- `save_blend_file` — Write — https://policylayer.com/tools/aryeon0228-blendermcp/save-blend-file.md
- `set_material` — Write — https://policylayer.com/tools/aryeon0228-blendermcp/set-material.md

## For agents

This record is a snapshot. Live verdicts and the full registry:

- Check every server in your MCP config at once: `npx -y policylayer stack`
- Vet a server before you add it: install the mcp-precheck skill — `npx skills add https://policylayer.com` (skill text: https://policylayer.com/skill.md)
- Query the registry over MCP: endpoint `https://api.policylayer.com/mcp` — tools `check_mcp_server`, `check_mcp_stack`, `check_tool`, `search_registry`, `get_change_events`

---

Source: the PolicyLayer MCP registry — one continuously verified record per MCP server. Full record: https://policylayer.com/registry?q=aryeon0228-blendermcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/aryeon0228-blendermcp