find_image_on_screen

Find an image on the screen and return its coordinates

SERVERMcp Windows SOURCEmukul975/mcp-windows-automation

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/mukul975-mcp-windows-automation/find-image-on-screen.md

WHAT IT DOES

What find_image_on_screen does on Mcp Windows

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

RISK

Why find_image_on_screen is rated Low

This tool performs screen analysis to locate images and return position data. It is purely observational with no side effects—no data is created, modified, deleted, executed, or financial transactions initiated. The blast radius of misuse is minimal; an attacker could gain knowledge of screen layout but cannot directly execute actions or access sensitive data beyond what is visually displayed.

From the tool's definition Tool name 'find_image_on_screen' and description 'Find an image on the screen and return its coordinates' indicate a query/detection operation that retrieves visual information without modifying system state.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs find_image_on_screen safely

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

find_image_on_screen Allowed

find_image_on_screen 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": {
    "find_image_on_screen": {}
  }
}

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

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

FAQ

Questions about find_image_on_screen

What does the find_image_on_screen tool do? +

Find an image on the screen and return its coordinates. It is categorised as a Read tool in the Mcp Windows MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on find_image_on_screen? +

Register the Mcp Windows MCP server in PolicyLayer and add a rule for find_image_on_screen: 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 Mcp Windows. Nothing to install.

What risk level is find_image_on_screen? +

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

Can I rate-limit find_image_on_screen? +

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

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

find_image_on_screen is provided by the Mcp Windows MCP server (mukul975/mcp-windows-automation). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Mcp Windows, and thousands of servers like it.

This server

All 441 Mcp Windows tools →

Across the catalogue

The MCP Attack Database →

Guides

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