AI agents use saveScene 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 or modifies files on disk (a JSON scene file), which falls under Write category. It's not Read (no data retrieval), not Execute (no arbitrary code execution), not Destructive (the file can be overwritten or deleted), and not Financial.
From the tool's definition The tool name is 'saveScene' and the description states it 'Save[s] the current scene to a JSON file in the scenes/ folder.' This involves creating/writing data to a file system.
Attacks that exploit this kind of access
Save the current scene to a JSON file in the scenes/ folder. Returns the file path. 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 saveScene: 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.
saveScene 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 saveScene 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 saveScene. 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.
saveScene 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 →