Take a screenshot using macOS screencapture
AI agents call take_screenshot to retrieve information from Apple Notifier without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshots are fundamentally read operations that retrieve visual data from the display. However, severity is elevated to 'medium' rather than 'low' because screenshots can capture sensitive information (passwords, private messages, financial data, personal documents) depending on what is currently displayed on screen.
From the tool's definition Tool description states 'Take a screenshot using macOS screencapture' - this captures visual information from the user's screen without modifying or deleting data.
Attacks that exploit this kind of access
Take a screenshot using macOS screencapture. It is categorised as a Read tool in the Apple Notifier MCP Server, which means it retrieves data without modifying state.
Register the Apple Notifier MCP server in PolicyLayer and add a rule for take_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 Apple Notifier. Nothing to install.
take_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 take_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 take_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.
take_screenshot is provided by the Apple Notifier MCP server (piatra-automation/apple-notifier-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 →