Take screenshot
AI agents call browser_screenshot to retrieve information from Browser Pool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Taking a screenshot is a passive observation operation that retrieves visual information from the current browser state without creating, modifying, deleting, or executing code. It has no side effects on the target system or data. This is purely informational, similar to a 'get' or 'read' operation.
From the tool's definition Tool name is 'browser_screenshot' with description 'Take screenshot'. The action is to capture a visual state of a web page without modifying it, querying data, or triggering side effects.
Attacks that exploit this kind of access
Take screenshot. It is categorised as a Read tool in the Browser Pool MCP Server, which means it retrieves data without modifying state.
Register the Browser Pool MCP server in PolicyLayer and add a rule for browser_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 Browser Pool. Nothing to install.
browser_screenshot is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the browser_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.
Set action: deny in the PolicyLayer policy for browser_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.
browser_screenshot is provided by the Browser Pool MCP server (omgeverdo/browser-pool-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
browser_screenshot is one line of Browser Pool's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →