AI agents use scene_export 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.
The tool generates and exports scene configuration data in JSON format intended for sharing and version control. While exporting itself is not destructive (data is not deleted), it creates a new serialized representation of state that could be committed to git.
From the tool's definition Tool description states 'Export current scene as shareable JSON (for git repos)' — this creates/generates a new data artifact (JSON export) that can be stored or transmitted, which is a write operation.
Attacks that exploit this kind of access
Export current scene as shareable JSON (for git repos). 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.
Register the Cartridge MCP server in PolicyLayer and add a rule for scene_export: 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.
scene_export 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 scene_export 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 scene_export. 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.
scene_export 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →