AI agents call loadSceneFromFile to retrieve information from Maige 3d without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and imports scene data from storage, which is a read-only operation. It loads a pre-existing scene definition without side effects beyond populating the 3D environment with that scene's data. While the scene itself may contain interactive elements or behaviors, the tool's core function is data retrieval.
From the tool's definition Tool performs a load operation that reads and retrieves a previously saved scene from the scenes/ folder. No data is modified, deleted, or executed.
Attacks that exploit this kind of access
Load a previously saved scene from the scenes/ folder by name. It is categorised as a Read tool in the Maige 3d MCP Server, which means it retrieves data without modifying state.
Register the Maige 3d MCP server in PolicyLayer and add a rule for loadSceneFromFile: 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.
loadSceneFromFile is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the loadSceneFromFile 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 loadSceneFromFile. 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.
loadSceneFromFile 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 →