capture_screenshot
AI agents call capture_screenshot to retrieve information from Uiautomation without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Capturing a screenshot retrieves visual state information from the screen without modifying or executing any operations. This is a Read operation (query/retrieve data with no side effects). The severity is low because screenshots do not alter system state, though they could potentially expose sensitive information on-screen.
From the tool's definition Tool named 'capture_screenshot' on a UI automation server; the server description indicates tools for 'inspect and automate Windows desktop UI elements' including 'exploring UI trees' and 'checking properties.' Screenshot capture is a passive observation…
Attacks that exploit this kind of access
capture_screenshot. It is categorised as a Read tool in the Uiautomation MCP Server, which means it retrieves data without modifying state.
Register the Uiautomation 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 Uiautomation. 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 Uiautomation MCP server (miloira/uiautomation-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 →