ui_read

Read the accessibility tree of the frontmost app (or specified app). Returns structured data about all visible UI elements including their roles, names, values, positions, and hierarchy. Use this to understand what UI elements are available before interacting with them. Requires Accessibility per...

SERVERAirMCP SOURCEairmcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

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

WHAT IT DOES

What ui_read does on AirMCP

AI agents call ui_read to retrieve information from AirMCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why ui_read is rated Low

This tool retrieves and queries data about the current state of UI elements (roles, names, values, positions, hierarchy) without modifying, creating, deleting, or executing actions. It is strictly informational and serves as a prerequisite for understanding the UI before interaction. The blast radius is minimal—it only exposes what is already visually accessible to the user.

From the tool's definition Tool name is 'ui_read' and description explicitly states it 'Read[s] the accessibility tree' and 'Returns structured data about all visible UI elements' with 'no side effects' implied by the read-only nature of querying UI state.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs ui_read 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_read, this is the rule to start with:

ui_read Allowed

ui_read is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "ui_read": {}
  }
}

ALLOW ONLY THIS TOOL → Instant setup, no code required.

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

FAQ

Questions about ui_read

What does the ui_read tool do? +

How do I enforce a policy on ui_read? +

Register the Air MCP server in PolicyLayer and add a rule for ui_read: 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_read? +

ui_read is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit ui_read? +

Yes. Add a rate_limit block to the ui_read 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_read completely? +

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

ui_read 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 →

Across the catalogue

claude_read_file on Claude Bridge → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →