snap_to_ground
Drop a GameObject straight down onto the surface below it (physics raycast). Works best on collider-less props (an object with its own collider may self-hit). Optional offset lifts it off the surface.
This record as markdown: /tools/sbox/snap-to-ground.md
What snap_to_ground does on Sbox
AI agents call snap_to_ground to permanently remove resources in Sbox, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why snap_to_ground is rated Critical
An AI agent that decides to call snap_to_ground doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Sbox is gone. There is no undo for destructive operations.
Attacks that exploit this kind of access
The rule that runs snap_to_ground 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 snap_to_ground, this is the rule to start with:
snap_to_ground is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect Sbox, apply this rule, and every snap_to_ground call is checked against it from then on.
Questions about snap_to_ground
Drop a GameObject straight down onto the surface below it (physics raycast). Works best on collider-less props (an object with its own collider may self-hit). Optional offset lifts it off the surface. It is categorised as a Destructive tool in the Sbox MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Sbox MCP server in PolicyLayer and add a rule for snap_to_ground: 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.
snap_to_ground is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the snap_to_ground 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 snap_to_ground. 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.
snap_to_ground 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.
Across the catalogue