scene_build · Cartridge MCP: Risk & Policy

WHAT IT DOES

What scene_build does on Cartridge

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

WHY IT NEEDS A POLICY

Why scene_build needs a policy

The tool creates/configures a scene by combining cartridges, skins, and role assignments. This is a write/create operation that assembles a new scene configuration. It does not appear to execute code, delete data, or involve financial operations. Confidence is moderate because the description is brief and doesn't detail exactly what 'building a scene' entails in terms of side effects.

From the tool's definition Build a scene with cartridge + skin + role assignments

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

scene_build Rate-limited

scene_build stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "scene_build": {
      "limits": [
        {
          "counter": "scene_build_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Cartridge, so you can run agents against it safely.

FAQ

Questions about scene_build

What does the scene_build tool do? +

Build a scene with cartridge + skin + role assignments. It is categorised as a Write tool in the Cartridge MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on scene_build? +

Register the Cartridge MCP server in PolicyLayer and add a rule for scene_build: 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 Cartridge. Nothing to install.

What risk level is scene_build? +

scene_build is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit scene_build? +

Yes. Add a rate_limit block to the scene_build 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.

How do I block scene_build completely? +

Set action: deny in the PolicyLayer policy for scene_build. 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.

What MCP server provides scene_build? +

scene_build is provided by the Cartridge MCP server (lucineer/cartridge-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.