perform_action · Uiautomation MCP: Risk & Policy

WHAT IT DOES

What perform_action does on Uiautomation

AI agents invoke perform_action to trigger actions in Uiautomation. 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 perform_action needs a policy

Given the server context — automating Windows desktop UI elements with actions like clicking and typing — 'perform_action' almost certainly triggers UI interactions (clicks, keystrokes, etc.) on the host system. This is Execute-category since it triggers external operations whose effects depend on arguments.

From the tool's definition Tool name 'perform_action' on a UI automation server described as enabling 'clicking and typing' and 'performing actions' on Windows desktop UI elements.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

perform_action Rate-limited

perform_action 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": {
    "perform_action": {
      "limits": [
        {
          "counter": "perform_action_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 Uiautomation, so you can run agents against it safely.

FAQ

Questions about perform_action

What does the perform_action tool do? +

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

How do I enforce a policy on perform_action? +

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

What risk level is perform_action? +

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

Can I rate-limit perform_action? +

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

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

perform_action is provided by the Uiautomation MCP server (miloira/uiautomation-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.