compare_images

THE RISK

Low Risk

Why compare_images needs a policy

This tool reads and analyzes two images using a Vision Language Model to compare them. It retrieves/queries visual data without modifying, executing, or deleting anything. The blast radius is low as it only produces analytical output.

From the tool's definition Compare two images using VLM

Documented attack patterns abuse exactly the kind of access compare_images gives an agent:

POLICY

How to control compare_images

PolicyLayer is an MCP gateway — it sits between your AI agents and Wayland, and nothing reaches the server without passing your rules. This is the rule we recommend for compare_images:

policy.json

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

compare_images is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register Wayland — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Wayland tools

Execute execute_action execute_action Execute capture_and_analyze Capture and analyze screenshot. Execute click_mouse Simulate left mouse click at current position. Execute drag_mouse drag_mouse Execute move_mouse move_mouse Execute scroll_mouse Scroll vertically (positive=up, negative=down). Read analyze_screenshot Analyze screenshot using VLM. Read capture_screenshot Capture screenshot with measurement rulers.

All 9 Wayland tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about compare_images

What does the compare_images tool do? +

Compare two images using VLM. It is categorised as a Read tool in the Wayland MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on compare_images? +

Register the Wayland MCP server in PolicyLayer and add a rule for compare_images: 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 Wayland. Nothing to install.

What risk level is compare_images? +

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

Can I rate-limit compare_images? +

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

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

compare_images is provided by the Wayland MCP server (someaka/wayland-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Wayland tool call.

Start from Wayland, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →