AI agents use exportStandaloneScene to create or update resources in Maige 3d — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Maige 3d environment.
This tool creates and generates a new file (standalone HTML), which is a Write operation that modifies the file system by adding new data. It is not Destructive because the operation is reversible (the exported file can be deleted). It is not Execute because it doesn't run arbitrary code - it exports/serializes existing scene data.
From the tool's definition Tool description states it 'Export the current scene as a standalone HTML file' - this creates and writes a new file artifact that persists outside the 3D environment.
Attacks that exploit this kind of access
Export the current scene as a standalone HTML file that plays in any browser without a server. It is categorised as a Write tool in the Maige 3d MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Maige 3d MCP server in PolicyLayer and add a rule for exportStandaloneScene: 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 Maige 3d. Nothing to install.
exportStandaloneScene 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 exportStandaloneScene 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 exportStandaloneScene. 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.
exportStandaloneScene is provided by the Maige 3d MCP server (m-ai-gexr/mcp-webgpu). 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 →