Generates a complete, compilable SceneView{} or ARSceneView{} Kotlin composable from a natural language description. Parses 40+ object types (furniture, vehicles, animals, food, buildings, nature), quantities ("two chairs", "3 spheres"), environment (indoor/outdoor/dark), and mode (3D or AR). Ret...
Part of the SceneView 3D & AR server.
Free to start. No card required.
AI agents use generate_scene to create or modify resources in SceneView 3D & AR. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call generate_scene repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach SceneView 3D & AR.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"generate_scene": {
"limits": [
{
"counter": "generate_scene_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full SceneView 3D & AR policy for all 63 tools.
These attack patterns abuse exactly the kind of access generate_scene gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Generates a complete, compilable SceneView{} or ARSceneView{} Kotlin composable from a natural language description. Parses 40+ object types (furniture, vehicles, animals, food, buildings, nature), quantities ("two chairs", "3 spheres"), environment (indoor/outdoor/dark), and mode (3D or AR). Returns working Kotlin code with proper engine setup, model loading, lighting, and ground plane. Use this when a user says "build me a scene with..." or describes a 3D scene they want to create.. It is categorised as a Write tool in the SceneView 3D & AR MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the SceneView 3D & AR MCP server in PolicyLayer and add a rule for generate_scene: 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 SceneView 3D & AR. Nothing to install.
generate_scene is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the generate_scene 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 generate_scene. 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.
generate_scene is provided by the SceneView 3D & AR MCP server (sceneview/gateway). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 63 SceneView 3D & AR tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.