ui_open_app

Open an application by name or bundle ID and return an accessibility tree summary of its windows and top-level UI elements. Requires Accessibility permissions.

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-open-app.md

WHAT IT DOES

What ui_open_app does on AirMCP

AI agents invoke ui_open_app 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_open_app is rated High

This tool launches arbitrary applications on the user's macOS system, which is an external operation with side effects. While it doesn't delete data or move money, executing arbitrary app launches could be misused to open malicious or unwanted applications. The accessibility tree read-back is secondary to the primary action of opening an app.

From the tool's definition "Open an application by name or bundle ID" — triggers an external operation (launching an app) whose effect depends on the argument provided

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs ui_open_app 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_open_app, this is the rule to start with:

ui_open_app Rate-limited

ui_open_app 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_open_app": {
      "limits": [
        {
          "counter": "ui_open_app_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_open_app call is checked against it from then on.

FAQ

Questions about ui_open_app

What does the ui_open_app tool do? +

Open an application by name or bundle ID and return an accessibility tree summary of its windows and top-level UI elements. Requires Accessibility permissions. 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_open_app? +

Register the Air MCP server in PolicyLayer and add a rule for ui_open_app: 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_open_app? +

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

Can I rate-limit ui_open_app? +

Yes. Add a rate_limit block to the ui_open_app 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_open_app completely? +

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

ui_open_app 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

disable_passenger_app on cPanel MCP Server → All high-risk MCP tools → The MCP Attack Database →

Guides

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