AI agents invoke show_desktop 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 OS-level action (Win+D) that affects the state of all open windows on the desktop. It is an external system operation with side effects (all windows are minimized), making it Execute. While the action is reversible (windows can be restored), it can disrupt active work and user sessions, warranting medium severity.
From the tool's definition Minimize all windows to show the desktop (Win+D equivalent)
Attacks that exploit this kind of access
Minimize all windows to show the desktop (Win+D equivalent). 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 show_desktop: 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.
show_desktop 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 show_desktop 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 show_desktop. 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.
show_desktop 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 →