Generates a complete, compilable Scene{} or ARScene{} 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 wor...
Part of the Sceneview MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use generate_scene to create or modify resources in Sceneview. 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. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Sceneview.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
generate_scene:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full Sceneview policy for all 26 tools.
Agents calling write-class tools like generate_scene have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
Generates a complete, compilable Scene{} or ARScene{} 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 MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Add a rule in your Intercept YAML policy under the tools section for generate_scene. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Sceneview MCP server.
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 Intercept 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 Intercept 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 MCP server (sceneview-mcp). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Open source. One binary. Zero dependencies.
npx -y @policylayer/intercept