lock_screen · xigua- MCP: Risk & Policy

WHAT IT DOES

What lock_screen does on xigua-MCP

AI agents invoke lock_screen 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.

WHY IT NEEDS A POLICY

Why lock_screen needs a policy

This tool triggers an external OS-level operation (locking the Windows screen) that affects the user's active session. It's not destructive in the sense of data loss, but it executes a system-level action with immediate real-world effect. Misuse by an AI agent could lock out the user unexpectedly, causing disruption.

From the tool's definition Lock the Windows screen immediately

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

lock_screen Rate-limited

lock_screen 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": {
    "lock_screen": {
      "limits": [
        {
          "counter": "lock_screen_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches xigua-MCP, so you can run agents against it safely.

FAQ

Questions about lock_screen

What does the lock_screen tool do? +

Lock the Windows screen immediately. 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.

How do I enforce a policy on lock_screen? +

Register the xigua- MCP server in PolicyLayer and add a rule for lock_screen: 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.

What risk level is lock_screen? +

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

Can I rate-limit lock_screen? +

Yes. Add a rate_limit block to the lock_screen 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 lock_screen completely? +

Set action: deny in the PolicyLayer policy for lock_screen. 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 lock_screen? +

lock_screen 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.