Take a screenshot of the page or element.
AI agents call take_screenshot to retrieve information from Chrome Devtools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshot capture is a passive read operation that observes the current state of the browser or DOM element without side effects, data modification, or code execution. While the tool accesses a live browser controlled by an agent, it cannot modify page content, execute arbitrary code, or cause destructive changes.
From the tool's definition Tool performs screenshot capture which retrieves visual state without modifying browser or page state. Description explicitly states 'Take a screenshot' indicating pure data retrieval.
Attacks that exploit this kind of access
Take a screenshot of the page or element. It is categorised as a Read tool in the Chrome Devtools MCP Server, which means it retrieves data without modifying state.
Register the Chrome Devtools MCP server in PolicyLayer and add a rule for take_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 Chrome Devtools. Nothing to install.
take_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 take_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 take_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.
take_screenshot is provided by the Chrome Devtools MCP server (shivamprasad99/chrome-devtools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →