Capture the current page (viewport or full scrolling page).
AI agents call screenshot_viewport to retrieve information from Visual Annotation MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Taking a screenshot is a non-destructive, side-effect-free information retrieval action. It reads the current state of a webpage and returns visual data. While screenshots could theoretically expose sensitive information displayed on screen, the tool itself performs no write, deletion, code execution, or financial operations.
From the tool's definition Tool description states 'Capture the current page' — a passive screenshot operation that retrieves visual data without modifying, deleting, or executing commands.
Attacks that exploit this kind of access
Capture the current page (viewport or full scrolling page). It is categorised as a Read tool in the Visual Annotation MCP MCP Server, which means it retrieves data without modifying state.
Register the Visual Annotation MCP server in PolicyLayer and add a rule for screenshot_viewport: 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 Visual Annotation MCP. Nothing to install.
screenshot_viewport 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_viewport 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_viewport. 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_viewport is provided by the Visual Annotation MCP server (mstocker1/visual_annotation_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 →