start_play

Enter play mode — starts running the game in the editor. Scripts execute, physics simulate, everything goes live

SERVERSbox SOURCEsbox-mcp-server

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/sbox/start-play.md

WHAT IT DOES

What start_play does on Sbox

AI agents invoke start_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.

RISK

Why start_play is rated High

This tool triggers execution of arbitrary game scripts and physics simulations within the s&box engine. While not destructive by itself, it activates live code execution whose effects depend on the current game state and scripts loaded in the editor. An AI agent could inadvertently cause unintended game behavior, resource consumption, or trigger scripts with side effects.

From the tool's definition Tool description states: 'starts running the game in the editor. Scripts execute, physics simulate, everything goes live' — explicitly indicates code execution and simulation startup.

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs start_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 start_play, this is the rule to start with:

start_play Rate-limited

start_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "start_play": {
      "limits": [
        {
          "counter": "start_play_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Sbox, apply this rule, and every start_play call is checked against it from then on.

FAQ

Questions about start_play

What does the start_play tool do? +

Enter play mode — starts running the game in the editor. Scripts execute, physics simulate, everything goes live. 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.

How do I enforce a policy on start_play? +

Register the Sbox MCP server in PolicyLayer and add a rule for start_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.

What risk level is start_play? +

start_play is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit start_play? +

Yes. Add a rate_limit block to the start_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.

How do I block start_play completely? +

Set action: deny in the PolicyLayer policy for start_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.

What MCP server provides start_play? +

start_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.

KEEP EXPLORING

More on Sbox, and thousands of servers like it.

This server

All 207 Sbox tools → High-risk tools on this server →

Across the catalogue

start_devtools_monitoring on Percepta MCP Server →team_manager_start_room on Team Manager MCP →music_play on Apple Apps MCP →start_etw_trace on Procmon → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →