stop_play
Exit play mode — stops the game and returns to editor. All runtime changes are discarded
This record as markdown: /tools/sbox/stop-play.md
What stop_play does on Sbox
AI agents invoke stop_play 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 stop_play is rated High
This tool executes a state-changing operation on the s&box game engine (stopping play mode and returning to editor). While not destructive in the permanent sense (changes are explicitly discarded), it is an Execute action because it triggers an external operation with side effects on the game engine's runtime state.
From the tool's definition Tool performs 'stop_play' which executes a command to exit play mode and stops the game, discarding runtime changes. This is a trigger of an external operation (game state transition) whose effects depend on context.
Attacks that exploit this kind of access
The rule that runs stop_play 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 stop_play, this is the rule to start with:
stop_play 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 stop_play call is checked against it from then on.
Questions about stop_play
Exit play mode — stops the game and returns to editor. All runtime changes are discarded. 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 stop_play: 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.
stop_play 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 stop_play 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 stop_play. 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.
stop_play 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