visual_compare

Compare current screen with saved baseline. Returns diff overlay on mismatch.

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/visual-compare.md

WHAT IT DOES

What visual_compare does on Claude Mobile

AI agents call visual_compare 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 visual_compare is rated Low

This tool reads and compares the current screen state against a saved baseline image, returning a visual diff. It only retrieves and analyzes data without modifying any state or triggering side effects.

From the tool's definition Compare current screen with saved baseline. Returns diff overlay on mismatch.

Attacks that exploit this kind of access

RECOMMENDED RULE

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

visual_compare Allowed

visual_compare 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": {
    "visual_compare": {}
  }
}

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 visual_compare call is checked against it from then on.

FAQ

Questions about visual_compare

What does the visual_compare tool do? +

Compare current screen with saved baseline. Returns diff overlay on mismatch. 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 visual_compare? +

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

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

Can I rate-limit visual_compare? +

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

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

visual_compare 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 →