puppeteer_screenshot

THE RISK

Low Risk

Why puppeteer_screenshot needs a policy

This tool captures a visual snapshot of a webpage or element. It reads/captures existing state without modifying data or triggering side effects. Screenshots are a read-only observation operation.

From the tool's definition Take a screenshot of the current page or a specific element

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

POLICY

How to control puppeteer_screenshot

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

policy.json

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

puppeteer_screenshot 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 MCP-Brave-Search — 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 MCP-Brave-Search tools

Destructive delete Delete one or more keys from Redis Execute puppeteer_evaluate Execute JavaScript in the browser console Execute puppeteer_navigate Navigate to a URL Execute puppeteer_hover Hover an element on the page Execute generate_image Generate images using EverArt Models and returns a clickable link to view the generated im Execute puppeteer_click Click an element on the page Execute puppeteer_fill Fill out an input field Execute puppeteer_select Select an element on the page with Select tag

All 59 MCP-Brave-Search 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 puppeteer_screenshot

What does the puppeteer_screenshot tool do? +

Take a screenshot of the current page or a specific element. It is categorised as a Read tool in the MCP-Brave-Search MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on puppeteer_screenshot? +

Register the MCP-Brave-Search MCP server in PolicyLayer and add a rule for puppeteer_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 MCP-Brave-Search. Nothing to install.

What risk level is puppeteer_screenshot? +

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

Can I rate-limit puppeteer_screenshot? +

Yes. Add a rate_limit block to the puppeteer_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 puppeteer_screenshot completely? +

Set action: deny in the PolicyLayer policy for puppeteer_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 puppeteer_screenshot? +

puppeteer_screenshot is provided by the MCP-Brave-Search MCP server (modelcontextprotocol/servers-archived). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP-Brave-Search tool call.

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

CHECK YOUR STACK →