# construct_object

A write tool on the Blender MCP server.

Agent View of the PolicyLayer registry record for `construct_object`. HTML page: https://policylayer.com/tools/sandraschi-blender-mcp/construct-object

## Facts

- Tool: `construct_object`
- Server: Blender (`sandraschi/blender-mcp`) — https://policylayer.com/tools/sandraschi-blender-mcp.md
- Homepage: https://github.com/sandraschi/blender-mcp
- Risk category: Write (Medium risk)
- Registry record: grade F, identity unverified
- Server rate-limited: no
- Parameters: 0
- Recommended policy verdict: Rate-limited

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

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

## Why construct_object is rated Medium

The name 'construct_object' suggests creating a new 3D object in Blender, which is a Write operation. The server description mentions creating objects and manipulating 3D scenes. However, the description is empty, which significantly lowers confidence. It could potentially execute scripts or destructively overwrite existing objects, but 'construct' most commonly implies creation/write.

From the tool's own definition: "Tool name 'construct_object' and server context of creating/manipulating 3D scenes in Blender"

## Use case

AI agents use construct_object to create or update resources in Blender, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Blender environment.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "construct_object": {
      "limits": [
        {
          "counter": "construct_object_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on Blender (80)

- `clear_scene` — Destructive — https://policylayer.com/tools/sandraschi-blender-mcp/clear-scene.md
- `agentic_blender_workflow` — Execute — https://policylayer.com/tools/sandraschi-blender-mcp/agentic-blender-workflow.md
- `blender_animation` — Execute — https://policylayer.com/tools/sandraschi-blender-mcp/blender-animation.md
- `blender_batch` — Execute — https://policylayer.com/tools/sandraschi-blender-mcp/blender-batch.md
- `blender_geonodes` — Execute — https://policylayer.com/tools/sandraschi-blender-mcp/blender-geonodes.md
- `blender_particles` — Execute — https://policylayer.com/tools/sandraschi-blender-mcp/blender-particles.md
- `blender_physics` — Execute — https://policylayer.com/tools/sandraschi-blender-mcp/blender-physics.md
- `blender_render` — Execute — https://policylayer.com/tools/sandraschi-blender-mcp/blender-render.md
- `blender_sculpt` — Execute — https://policylayer.com/tools/sandraschi-blender-mcp/blender-sculpt.md
- `blender_transform` — Execute — https://policylayer.com/tools/sandraschi-blender-mcp/blender-transform.md
- `blender_workflow` — Execute — https://policylayer.com/tools/sandraschi-blender-mcp/blender-workflow.md
- `generate_blender_script` — Execute — https://policylayer.com/tools/sandraschi-blender-mcp/generate-blender-script.md
- `intelligent_3d_processing` — Execute — https://policylayer.com/tools/sandraschi-blender-mcp/intelligent-3d-processing.md
- `manage_blender_addons` — Execute — https://policylayer.com/tools/sandraschi-blender-mcp/manage-blender-addons.md
- `script_execute` — Execute — https://policylayer.com/tools/sandraschi-blender-mcp/script-execute.md
- `blender_addons` — Other — https://policylayer.com/tools/sandraschi-blender-mcp/blender-addons.md
- `blender_atlasing` — Other — https://policylayer.com/tools/sandraschi-blender-mcp/blender-atlasing.md
- `blender_categories` — Other — https://policylayer.com/tools/sandraschi-blender-mcp/blender-categories.md
- `blender_compositor` — Other — https://policylayer.com/tools/sandraschi-blender-mcp/blender-compositor.md
- `blender_download` — Other — https://policylayer.com/tools/sandraschi-blender-mcp/blender-download.md
- `blender_furniture` — Other — https://policylayer.com/tools/sandraschi-blender-mcp/blender-furniture.md
- `blender_grease_pencil` — Other — https://policylayer.com/tools/sandraschi-blender-mcp/blender-grease-pencil.md
- `blender_health_check` — Other — https://policylayer.com/tools/sandraschi-blender-mcp/blender-health-check.md
- `blender_help` — Other — https://policylayer.com/tools/sandraschi-blender-mcp/blender-help.md
- `blender_materials_baking` — Other — https://policylayer.com/tools/sandraschi-blender-mcp/blender-materials-baking.md
- `blender_performance_monitor` — Other — https://policylayer.com/tools/sandraschi-blender-mcp/blender-performance-monitor.md
- `blender_rigging` — Other — https://policylayer.com/tools/sandraschi-blender-mcp/blender-rigging.md
- `blender_selection` — Other — https://policylayer.com/tools/sandraschi-blender-mcp/blender-selection.md
- `blender_session` — Other — https://policylayer.com/tools/sandraschi-blender-mcp/blender-session.md
- `blender_shapekeys` — Other — https://policylayer.com/tools/sandraschi-blender-mcp/blender-shapekeys.md
- …and 50 more: https://policylayer.com/tools/sandraschi-blender-mcp.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=sandraschi-blender-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/sandraschi-blender-mcp