simulate_input
Synthesize player input during PLAY mode so behavior can be verified without a human at the keyboard: press/hold/release a named input action (e.g.
This record as markdown: /tools/sbox/simulate-input.md
What simulate_input does on Sbox
AI agents invoke simulate_input 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 simulate_input is rated High
This tool simulates/synthesizes player input actions in a running game engine (PLAY mode), which constitutes triggering external operations within the game runtime. It executes synthetic input events that drive game behavior, making it an Execute-category tool. Misuse could trigger unintended in-game actions or manipulate game state in unpredictable ways, warranting high severity.
From the tool's definition Synthesize player input during PLAY mode so behavior can be verified without a human at the keyboard: press/hold/release a named input action
Attacks that exploit this kind of access
The rule that runs simulate_input 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 simulate_input, this is the rule to start with:
simulate_input 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 simulate_input call is checked against it from then on.
Questions about simulate_input
Synthesize player input during PLAY mode so behavior can be verified without a human at the keyboard: press/hold/release a named input action (e.g. 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 simulate_input: 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.
simulate_input 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 simulate_input 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 simulate_input. 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.
simulate_input 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