This record as markdown: /tools/sbox/assign-model.md
What assign_model does on Sbox
AI agents use assign_model to create or update resources in Sbox, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Sbox environment.
Why assign_model is rated Medium
This tool creates or modifies game object state (assigning a 3D model) without permanently deleting data or executing arbitrary code. It fits the Write category because the change is reversible — a different model can be assigned later.
From the tool's definition Tool description explicitly states 'Set a 3D model on a GameObject' — this modifies a game object's properties by assigning/changing a model asset, which is a reversible write operation.
Attacks that exploit this kind of access
The rule that runs assign_model 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 assign_model, this is the rule to start with:
assign_model stays usable, but capped: an agent stuck in a loop can't make hundreds of changes 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 assign_model call is checked against it from then on.
Questions about assign_model
Set a 3D model on a GameObject. It is categorised as a Write tool in the Sbox MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Sbox MCP server in PolicyLayer and add a rule for assign_model: 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.
assign_model 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 assign_model 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 assign_model. 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.
assign_model 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