select_object
Select a GameObject in the editor (highlights it in the hierarchy and scene view)
This record as markdown: /tools/sbox/select-object.md
What select_object does on Sbox
AI agents invoke select_object to trigger actions in Sbox. 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.
Why select_object is rated High
Selecting an object in the editor is an external operation that changes the editor's state (selection/focus), making it Execute rather than Read. However, it has no side effects on data, making the blast radius very low.
From the tool's definition 'Select a GameObject in the editor (highlights it in the hierarchy and scene view)' — triggers an editor UI action/operation
Attacks that exploit this kind of access
The rule that runs select_object safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Sbox, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For select_object, this is the rule to start with:
select_object stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Sbox, apply this rule, and every select_object call is checked against it from then on.
Questions about select_object
Select a GameObject in the editor (highlights it in the hierarchy and scene view). It is categorised as a Execute tool in the Sbox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Sbox MCP server in PolicyLayer and add a rule for select_object: 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 Sbox. Nothing to install.
select_object 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 select_object 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 select_object. 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.
select_object is provided by the Sbox MCP server (sbox-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Sbox, and thousands of servers like it.
This server
Across the catalogue