# generate_3d_model

Turn a text prompt into a textured, downloadable 3D model (GLB). Free and keyless. Describe a SINGLE object, character, or creature: "a brass mid-century desk lamp", not a whole scene. Returns the model URL plus links that open it in the viewer, in the user's room through their phone camera, and in the AR studio. Use kind:"avatar" for a character: it comes back rigged, so it idles and animates instead of standing in a T-pose.

Agent View of the PolicyLayer registry record for `generate_3d_model`. HTML page: https://policylayer.com/tools/3d-ar-studio-mcp/generate-3d-model

## Facts

- Tool: `generate_3d_model`
- Server: 3d Ar Studio (`3d-ar-studio-mcp`) — https://policylayer.com/tools/3d-ar-studio-mcp.md
- Install: `npx -y 3d-ar-studio-mcp`
- Homepage: https://www.npmjs.com/package/3d-ar-studio-mcp
- Risk category: Write (Medium risk)
- Registry record: grade C, identity unverified
- Server rate-limited: no
- Parameters: 3 (1 required)
- Recommended policy verdict: Rate-limited

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `kind` | string | no | model (a prop, default), avatar (a rigged character), or mesh (art-directed, prompt refined first). |
| `tier` | string | no | Detail level. Higher is slower. |
| `prompt` | string | yes | The single object or character to model. |

Parameters from the server's own tool schema.

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

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "generate_3d_model",
    "arguments": {
      "prompt": "<prompt>"
    }
  }
}
```

## Why generate_3d_model is rated Medium

An AI agent can call generate_3d_model faster than any human can review: one bad instruction and it creates or modifies resources in 3d Ar Studio by the hundred, each call as confident as the last.

## Use case

AI agents use generate_3d_model to create or update resources in 3d Ar Studio, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your 3d Ar Studio environment.

## Recommended policy (PolicyLayer)

Verdict: **Rate-limited**. Enforced by the PolicyLayer MCP gateway (https://policylayer.com/mcp-gateway) before a call reaches 3d Ar Studio:

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "generate_3d_model": {
      "limits": [
        {
          "counter": "generate_3d_model_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}
```

## Other tools on 3d Ar Studio (5)

- `check_generation` — Read — https://policylayer.com/tools/3d-ar-studio-mcp/check-generation.md
- `compose_ar_scene` — Read — https://policylayer.com/tools/3d-ar-studio-mcp/compose-ar-scene.md
- `search_models` — Read — https://policylayer.com/tools/3d-ar-studio-mcp/search-models.md
- `create_ar_page` — Write — https://policylayer.com/tools/3d-ar-studio-mcp/create-ar-page.md
- `export_ar` — Write — https://policylayer.com/tools/3d-ar-studio-mcp/export-ar.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=3d-ar-studio-mcp · API: https://policylayer.com/registry/api · Policy library: https://policylayer.com/policies/3d-ar-studio-mcp