ui_perform_action

Find a UI element by locator (role + title/value) and perform an accessibility action on it.

SERVERAirMCP SOURCEairmcp

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/heznpc-airmcp/ui-perform-action.md

WHAT IT DOES

What ui_perform_action does on AirMCP

AI agents invoke ui_perform_action to trigger actions in AirMCP. 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.

RISK

Why ui_perform_action is rated High

This tool interacts with arbitrary UI elements via accessibility actions, effectively allowing an AI agent to click buttons, activate controls, or trigger any UI operation in any application. This constitutes executing external operations whose effects depend on the arguments provided, with a high blast radius since it can manipulate any accessible UI element across the entire macOS environment.

From the tool's definition "Find a UI element by locator (role + title/value) and perform an accessibility action on it"

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs ui_perform_action safely

PolicyLayer is an MCP gateway: it sits between your AI agents and AirMCP, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ui_perform_action, this is the rule to start with:

ui_perform_action Rate-limited

ui_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": {
    "ui_perform_action": {
      "limits": [
        {
          "counter": "ui_perform_action_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect AirMCP, apply this rule, and every ui_perform_action call is checked against it from then on.

FAQ

Questions about ui_perform_action

What does the ui_perform_action tool do? +

Find a UI element by locator (role + title/value) and perform an accessibility action on it. It is categorised as a Execute tool in the AirMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ui_perform_action? +

Register the Air MCP server in PolicyLayer and add a rule for ui_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 AirMCP. Nothing to install.

What risk level is ui_perform_action? +

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

Can I rate-limit ui_perform_action? +

Yes. Add a rate_limit block to the ui_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 ui_perform_action completely? +

Set action: deny in the PolicyLayer policy for ui_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 ui_perform_action? +

ui_perform_action is provided by the Air MCP server (airmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Air, and thousands of servers like it.

This server

All 279 Air tools → High-risk tools on this server →

Across the catalogue

qt_trigger_action on Qt → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →