screenshot_compare · Browsershot MCP: Risk & Policy

WHAT IT DOES

What screenshot_compare does on Browsershot MCP

AI agents invoke screenshot_compare to trigger actions in Browsershot MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why screenshot_compare needs a policy

This tool launches browser instances via Puppeteer to capture screenshots at various viewport widths. While the primary output is read-like (images), the act of driving a headless browser, loading arbitrary URLs, and executing page scripts constitutes external execution.

From the tool's definition 'Take screenshots at multiple viewport widths' — triggers Puppeteer browser execution across multiple viewports, performing external browser automation operations

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

screenshot_compare Rate-limited

screenshot_compare stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "screenshot_compare": {
      "limits": [
        {
          "counter": "screenshot_compare_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Browsershot MCP, so you can run agents against it safely.

FAQ

Questions about screenshot_compare

What does the screenshot_compare tool do? +

Take screenshots at multiple viewport widths to compare responsive layouts. It is categorised as a Execute tool in the Browsershot MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on screenshot_compare? +

Register the Browsershot MCP server in PolicyLayer and add a rule for screenshot_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 Browsershot MCP. Nothing to install.

What risk level is screenshot_compare? +

screenshot_compare is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit screenshot_compare? +

Yes. Add a rate_limit block to the screenshot_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 screenshot_compare completely? +

Set action: deny in the PolicyLayer policy for screenshot_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 screenshot_compare? +

screenshot_compare is provided by the Browsershot MCP server (kjaiswal/browsershot-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.