# compose_ar_scene

Arrange several models into a single scene and get one link that reopens it exactly: same models, same positions, rotations and scales. Open that link on a phone and the whole arrangement stands in the real room. Coordinates are metres on the floor: x is right, z is forward with negative values further away, so { x: 0, z: -2 } is two metres in front of the viewer. This is the tool to reach for when someone wants to see more than one thing at once.

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

## Facts

- Tool: `compose_ar_scene`
- 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: Read (Low risk)
- Registry record: grade C, identity unverified
- Server rate-limited: no
- Parameters: 3 (1 required)
- Recommended policy verdict: Allowed

## Parameters

| Parameter | Type | Required | Description |
| --- | --- | --- | --- |
| `title` | string | no | A name for the scene, used in the summary. |
| `models` | array | yes | The models to arrange, in placement order. |
| `page_url` | string | no | The page hosting the studio. Defaults to the hosted demo. |

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": "compose_ar_scene",
    "arguments": {
      "models": []
    }
  }
}
```

## Why compose_ar_scene is rated Low

Even though compose_ar_scene only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.

## Use case

AI agents call compose_ar_scene to retrieve information from 3d Ar Studio without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

## Recommended policy (PolicyLayer)

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

```json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "compose_ar_scene": {}
  }
}
```

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

- `check_generation` — Read — https://policylayer.com/tools/3d-ar-studio-mcp/check-generation.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
- `generate_3d_model` — Write — https://policylayer.com/tools/3d-ar-studio-mcp/generate-3d-model.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