replace_model
Swap the model on one object (id) or many (ids) — e.g. retheme a row of props in one call.
This record as markdown: /tools/sbox/replace-model.md
What replace_model does on Sbox
AI agents use replace_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 replace_model is rated Medium
This tool creates or modifies data reversibly within the s&box game engine. It changes object properties (model assignments) without deleting objects or executing arbitrary code. The blast radius is medium because widespread model swaps could degrade the game scene aesthetically or functionally, but the operation is not destructive or irreversible. Write is the appropriate category.
From the tool's definition Tool description states 'Swap the model on one object (id) or many (ids)' — this modifies properties of existing game objects by replacing their visual representation. The action is reversible (can swap back to a previous model).
Attacks that exploit this kind of access
The rule that runs replace_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 replace_model, this is the rule to start with:
replace_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 replace_model call is checked against it from then on.
Questions about replace_model
Swap the model on one object (id) or many (ids) — e.g. retheme a row of props in one call. 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 replace_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.
replace_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 replace_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 replace_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.
replace_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