Selects a GameObject in the Editor by name.
AI agents invoke set_selection to trigger actions in MCP For Unity. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Changing the editor selection is an external operation within the Unity Editor that affects UI state and can influence subsequent editor operations. It doesn't read data, write persistent data, or destroy anything, but it does trigger a state change in the external Unity Editor environment. Severity is low as the blast radius is minimal — at worst it changes which object is selected, which is easily reversible.
From the tool's definition 'Selects a GameObject in the Editor by name' — triggers an external operation (changing the Unity Editor's selection state)
Attacks that exploit this kind of access
Selects a GameObject in the Editor by name. It is categorised as a Execute tool in the MCP For Unity MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP For Unity MCP server in PolicyLayer and add a rule for set_selection: 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.
set_selection is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the set_selection 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 set_selection. 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.
set_selection 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 →