Modifies the transform (Position, Rotation, Scale) of a GameObject.
AI agents use modify_transform to create or update resources in MCP For Unity — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP For Unity environment.
This tool updates existing properties (position, rotation, scale) of a Unity GameObject. These are reversible modifications to scene data — no code execution, deletion, or financial action involved. Misuse could displace or distort objects in the scene, but changes can typically be undone via Unity's undo stack.
From the tool's definition Modifies the transform (Position, Rotation, Scale) of a GameObject
Attacks that exploit this kind of access
Modifies the transform (Position, Rotation, Scale) of a GameObject. It is categorised as a Write tool in the MCP For Unity MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP For Unity MCP server in PolicyLayer and add a rule for modify_transform: 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 MCP For Unity. Nothing to install.
modify_transform 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 modify_transform 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 modify_transform. 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.
modify_transform is provided by the MCP For Unity MCP server (yunuscan/mcpforunity). 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 →