AI agents call get_scene_objects to retrieve information from Unity without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves scene metadata (GameObject names, paths, tags, layers) from a Unity project. It performs only read operations on the knowledge graph without creating, modifying, deleting, or executing any code. The blast radius of misuse is minimal—an AI agent cannot harm the project by reading scene structure.
From the tool's definition Tool description states it 'Get[s] all GameObjects in a specific scene' and 'Returns names, paths, tags, and layer info.' The verb 'Get' and 'Returns' indicate pure data retrieval with no modification or side effects.
Attacks that exploit this kind of access
Get all GameObjects in a specific scene. Returns names, paths, tags, and layer info. It is categorised as a Read tool in the Unity MCP Server, which means it retrieves data without modifying state.
Register the Unity MCP server in PolicyLayer and add a rule for get_scene_objects: 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 Unity. Nothing to install.
get_scene_objects 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 get_scene_objects 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 get_scene_objects. 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.
get_scene_objects is provided by the Unity MCP server (verysleepylemon/unity-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 →