screenshot · Browsershot MCP: Risk & Policy

WHAT IT DOES

What screenshot does on Browsershot MCP

AI agents invoke screenshot 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 needs a policy

This tool executes a headless browser session to visit a caller-supplied URL, which constitutes running an external operation. While it appears read-like (capturing a screenshot), it actively executes browser automation and makes outbound network connections to arbitrary URLs, placing it in the Execute category.

From the tool's definition 'Take a browser screenshot of a URL' — launches a browser (Puppeteer) and navigates to an arbitrary URL, triggering external network requests and browser execution

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

screenshot Rate-limited

screenshot 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": {
      "limits": [
        {
          "counter": "screenshot_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

What does the screenshot tool do? +

Take a browser screenshot of a URL. Returns the image file path. 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? +

Register the Browsershot MCP server in PolicyLayer and add a rule for screenshot: 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? +

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

Can I rate-limit screenshot? +

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

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

screenshot 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.