screen_annotate

Screenshot with numbered bounding boxes on UI elements (Android/iOS)

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/screen-annotate.md

WHAT IT DOES

What screen_annotate does on Claude Mobile

AI agents call screen_annotate 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 screen_annotate is rated Low

This tool captures and annotates a screenshot of the device screen. It only reads/captures visual state of the UI and adds annotations (bounding boxes) for display purposes. No data is modified, no commands are executed, and there are no destructive or financial implications. It is purely a read/observation operation.

From the tool's definition Screenshot with numbered bounding boxes on UI elements

Attacks that exploit this kind of access

RECOMMENDED RULE

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

screen_annotate Allowed

screen_annotate 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": {
    "screen_annotate": {}
  }
}

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 screen_annotate call is checked against it from then on.

FAQ

Questions about screen_annotate

What does the screen_annotate tool do? +

Screenshot with numbered bounding boxes on UI elements (Android/iOS). 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 screen_annotate? +

Register the Claude Mobile MCP server in PolicyLayer and add a rule for screen_annotate: 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 screen_annotate? +

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

Can I rate-limit screen_annotate? +

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

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

screen_annotate 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 →