ui_analyze

Structured screen analysis: buttons, inputs, text, scrollable areas, dialogs

SERVERClaude Mobile SOURCEalexgladkov/claude-in-mobile

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/alexgladkov-claude-in-mobile/ui-analyze.md

WHAT IT DOES

What ui_analyze does on Claude Mobile

AI agents call ui_analyze to retrieve information from Claude Mobile 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_analyze is rated Low

This tool retrieves and analyzes visual/structural information from the mobile device screen. It extracts data about UI components without modifying device state, executing commands, or causing side effects. This is a pure information-gathering operation, consistent with the Read category for tools that query or retrieve data with no side effects.

From the tool's definition Tool performs 'Structured screen analysis' of UI elements (buttons, inputs, text, scrollable areas, dialogs) with no mention of modification, deletion, or execution of device actions.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs ui_analyze safely

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

ui_analyze Allowed

ui_analyze 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_analyze": {}
  }
}

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

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

FAQ

Questions about ui_analyze

What does the ui_analyze tool do? +

Structured screen analysis: buttons, inputs, text, scrollable areas, dialogs. It is categorised as a Read tool in the Claude Mobile MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on ui_analyze? +

Register the Claude Mobile MCP server in PolicyLayer and add a rule for ui_analyze: 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 Claude Mobile. Nothing to install.

What risk level is ui_analyze? +

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

Can I rate-limit ui_analyze? +

Yes. Add a rate_limit block to the ui_analyze 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_analyze completely? +

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

ui_analyze is provided by the Claude Mobile MCP server (alexgladkov/claude-in-mobile). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Claude Mobile, and thousands of servers like it.

This server

All 198 Claude Mobile tools →

Across the catalogue

The MCP Attack Database →

Guides

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