Low Risk

screenshot

Capture full-page PNG screenshot of specified URL with configurable wait time

How to control screenshot ↓

What screenshot does on Crawl4ai

AI agents call screenshot to retrieve information from Crawl4ai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why screenshot needs a policy

Screenshots are a passive read operation that retrieves visual data from a webpage without side effects. The tool captures the current state of a URL but does not modify, execute, or destroy any data. Low severity because misuse (e.g., screenshotting sensitive pages) would at worst expose information already visible to the agent, with no capability to alter systems or data.

From the tool's definition Tool name 'screenshot' and description 'Capture full-page PNG screenshot of specified URL with configurable wait time' indicate data retrieval without modification. No parameters suggest deletion, creation, execution of arbitrary code, or financial operations.

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

How to control screenshot

PolicyLayer is an MCP gateway — it sits between your AI agents and Crawl4ai, and nothing reaches the server without passing your rules. This is the rule we recommend for screenshot:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "screenshot": {}
  }
}

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

  1. Create a free account and register Crawl4ai — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about screenshot

What does the screenshot tool do? +

Capture full-page PNG screenshot of specified URL with configurable wait time. It is categorised as a Read tool in the Crawl4ai MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on screenshot? +

Register the Crawl4ai 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 Crawl4ai. Nothing to install.

What risk level is screenshot? +

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

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 Crawl4ai MCP server (stgmt/crawl4ai-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Crawl4ai tool call.

Start from Crawl4ai, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

Free to start. No card required.

6 Crawl4ai tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.