key · Desk MCP: Risk & Policy

WHAT IT DOES

What key does on Desk

AI agents invoke key to trigger actions in Desk. 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 key needs a policy

Given the server's purpose (desktop automation via xdotool and XDG Desktop Portals) and sibling tools for input simulation, 'key' almost certainly sends keyboard key events (e.g., hotkeys, shortcuts, special keys). This constitutes executing external operations/actions in a running environment. Empty description lowers confidence but the context is strong.

From the tool's definition Tool name 'key' on a desktop automation server with sibling tools including 'click', 'type_text', 'scroll' — context strongly implies keyboard key press simulation via xdotool (e.g., xdotool key). Description is empty.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

key Rate-limited

key 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": {
    "key": {
      "limits": [
        {
          "counter": "key_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 Desk, so you can run agents against it safely.

FAQ

Questions about key

What does the key tool do? +

key. It is categorised as a Execute tool in the Desk MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on key? +

Register the Desk MCP server in PolicyLayer and add a rule for key: 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 Desk. Nothing to install.

What risk level is key? +

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

Can I rate-limit key? +

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

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

key is provided by the Desk MCP server (kpihx/desk-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.