Screeny

Captures visual snapshots of active macOS windows and returns them as image data that AI agents can process. Implements native macOS APIs (likely CGWindowListCreateImage or similar) to grab window content at the pixel level, enabling agents to understand UI state, form layouts, and visual information without parsing HTML or DOM structures. Privacy-first design keeps all image data local to the machine.

Exposes screenshot capture as an MCP tool that AI agents can invoke through standard function-calling interfaces. Implements the MCP server protocol to register a callable tool with schema validation, allowing agents to request screenshots with optional parameters (window ID, region bounds, format). Handles tool invocation routing and response serialization back to the agent.

Ensures all screenshot data remains on the local machine without transmission to external servers or cloud APIs. Implements a local-only architecture where image capture, storage, and delivery happen entirely within the MCP server process. No telemetry, no image logging to external services, and no intermediate cloud processing steps.

Allows agents to request screenshots of specific windows by window identifier or title matching, rather than capturing the entire screen. Implements window enumeration and filtering logic to locate target windows and capture only their content. Supports optional region-of-interest cropping to capture specific UI elements within a window.

Enables agents to capture screenshots before and after taking actions (e.g., clicking buttons, typing text), creating a visual feedback loop for verification and error detection. Agents can request screenshots, take an action via another tool, then request another screenshot to verify the action succeeded. Supports sequential screenshot requests within a single agent reasoning step.