截取当前页面截图，返回base64编码图片
AI agents call page_screenshot to retrieve information from Js Reverse without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshot capture is a non-destructive, read-only operation that queries the visual state of a webpage without creating, modifying, or deleting data. It produces no side effects beyond obtaining information. While potentially sensitive in terms of what data may appear on screen, the tool's mechanics are purely retrieval-based, placing it firmly in the Read category.
From the tool's definition The tool 'page_screenshot' captures the current page screenshot and returns a base64-encoded image. The description uses '截取' (capture/take) and '返回' (return), indicating it retrieves visual data without modifying state. The verb is observational only.
Attacks that exploit this kind of access
截取当前页面截图，返回base64编码图片. It is categorised as a Read tool in the Js Reverse MCP Server, which means it retrieves data without modifying state.
Register the Js Reverse MCP server in PolicyLayer and add a rule for page_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 Js Reverse. Nothing to install.
page_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 page_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 page_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.
page_screenshot is provided by the Js Reverse MCP server (jenn619/js-reverse-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 →