AI agents invoke turn_off_display to trigger actions in xigua-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 (powering off the display) that affects the user's system state. It is reversible (display can be turned back on) but it executes a system-level action rather than simply reading or writing data. Misuse could disrupt user sessions or hide activity from the user.
From the tool's definition '仅关闭显示器(电脑保持运行,仅Windows)' — turns off the display monitor while the computer keeps running
Attacks that exploit this kind of access
仅关闭显示器(电脑保持运行,仅Windows). It is categorised as a Execute tool in the xigua-MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the xigua- MCP server in PolicyLayer and add a rule for turn_off_display: 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 xigua-MCP. Nothing to install.
turn_off_display 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_off_display 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_off_display. 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_off_display is provided by the xigua- MCP server (xiguaxiaome/xigua-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 →