Take a screenshot of a webpage at mobile viewport size
AI agents call screenshot_url_mobile to retrieve information from Screenshot without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool captures a read-only screenshot of a webpage at mobile viewport dimensions using the ScreenshotOne API. It only fetches/renders and returns visual data without any side effects on external systems. The only risk is that it could be used to capture sensitive pages, but the blast radius is low.
From the tool's definition 'Take a screenshot of a webpage' — retrieves a visual snapshot of a URL; no data is created, modified, or deleted.
Attacks that exploit this kind of access
Take a screenshot of a webpage at mobile viewport size. It is categorised as a Read tool in the Screenshot MCP Server, which means it retrieves data without modifying state.
Register the Screenshot MCP server in PolicyLayer and add a rule for screenshot_url_mobile: 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 Screenshot. Nothing to install.
screenshot_url_mobile 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 screenshot_url_mobile 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 screenshot_url_mobile. 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.
screenshot_url_mobile is provided by the Screenshot MCP server (rumblingb/screenshot-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 →