Turn off the screen (device remains active for control/casting)
AI agents invoke turn_screen_off to trigger actions in AutoBot MCP. 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.
This tool triggers an external hardware operation on an Android device — turning off its screen. While not destructive or financial, it executes a device-level action that changes the device's state. The device remains active, so it's reversible, but it's an operation that affects the physical device's behavior rather than a simple data read or write.
From the tool's definition Turn off the screen (device remains active for control/casting)
Attacks that exploit this kind of access
Turn off the screen (device remains active for control/casting). It is categorised as a Execute tool in the AutoBot MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the AutoBot MCP server in PolicyLayer and add a rule for turn_screen_off: 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 AutoBot MCP. Nothing to install.
turn_screen_off 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 turn_screen_off 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 turn_screen_off. 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.
turn_screen_off is provided by the AutoBot MCP server (yz0903/autobot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →