Take a screenshot of the current page with labeled elements
AI agents call screenshot to retrieve information from Atlas Browser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The screenshot tool only observes and captures the visual state of a webpage. It performs no write operations, does not execute code or commands, and does not modify any data. It is purely informational, returning an image of what is currently displayed. This is a classic Read operation with minimal security risk.
From the tool's definition Takes a screenshot of the current page with labeled elements - a retrieval operation with no data modification or external effects.
Attacks that exploit this kind of access
Take a screenshot of the current page with labeled elements. It is categorised as a Read tool in the Atlas Browser MCP Server, which means it retrieves data without modifying state.
Register the Atlas Browser MCP server in PolicyLayer and add a rule for 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 Atlas Browser. Nothing to install.
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 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 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.
screenshot is provided by the Atlas Browser MCP server (lingtravel/atlas-browser). 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 →