take_screenshot
AI agents call take_screenshot to retrieve information from macOS Control MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Screenshot capture is a read-only operation that retrieves visual information from the display without modifying system state, creating, deleting, or executing code. While sensitive information might appear in screenshots, the tool itself performs no side effects. Severity is low because screenshot alone poses minimal risk unless combined with other tools that act on the captured information.
From the tool's definition Tool name 'take_screenshot' and server context describing 'screen capture' capability. Description is empty but name and sibling tools clearly indicate this captures visual screen state.
Attacks that exploit this kind of access
take_screenshot. It is categorised as a Read tool in the macOS Control MCP Server MCP Server, which means it retrieves data without modifying state.
Register the macOS Control MCP Server 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 macOS Control MCP Server. 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 macOS Control MCP Server MCP server (lodimup/macos-control-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 →