AI agents call capture_screenshot to retrieve information from Macinput without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Capturing a screenshot is fundamentally a read operation that retrieves visual data from the screen without modifying system state or data. However, severity is elevated to 'medium' rather than 'low' because screenshots can expose sensitive information (passwords, PII, credentials, proprietary data visible on screen), creating a meaningful risk if an AI agent misuses this capability without proper consent or context…
From the tool's definition Tool captures and returns a screenshot of the full screen as a PNG file. The description indicates 'Capture the full screen and return a temporary PNG path' with no modification, deletion, or execution of external processes mentioned.
Attacks that exploit this kind of access
Capture the full screen and return a temporary PNG path. It is categorised as a Read tool in the Macinput MCP Server, which means it retrieves data without modifying state.
Register the Macinput MCP server in PolicyLayer and add a rule for capture_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 Macinput. Nothing to install.
capture_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 capture_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 capture_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.
capture_screenshot is provided by the Macinput MCP server (sigma711/macinput). 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 →