Take a screenshot of the current page
AI agents call chrome_screenshot to retrieve information from Chrome MCP Stealth without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshots retrieve visual information from a webpage without side effects. This is a passive data retrieval operation similar to 'get' or 'fetch'. While the server enables browser automation for potentially deceptive purposes (bot detection bypass), the screenshot tool itself only captures and returns data without altering state or executing arbitrary operations.
From the tool's definition Tool name 'chrome_screenshot' and description 'Take a screenshot of the current page' indicate a read-only operation that captures visual data without modifying, deleting, or executing code on the target website.
Attacks that exploit this kind of access
Take a screenshot of the current page. It is categorised as a Read tool in the Chrome MCP Stealth MCP Server, which means it retrieves data without modifying state.
Register the Chrome MCP Stealth MCP server in PolicyLayer and add a rule for chrome_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 MCP Stealth. Nothing to install.
chrome_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 chrome_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 chrome_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.
chrome_screenshot is provided by the Chrome MCP Stealth MCP server (riaan-fourie/chrome-mcp-stealth). 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 →