This is a Model Context Protocol server that exposes Windows desktop automation and system administration functions to large language models. It provides programmatic control of mouse, keyboard, windows, and UI elements on Windows through simulated user input, while also enabling LLMs to manage the Windows registry, processes, files, and execute PowerShell commands through a remote interface.
The server supports multiple transport protocols including stdio, SSE, and streamable HTTP, allowing flexible integration with different language model clients. It implements OAuth 2.0 with PKCE for secure remote access, along with bearer token authentication, TLS encryption, IP address restrictions, and SSRF protection to control access to Windows system functions. The server uses a TOML configuration system for storing settings, tool whitelists, and security policies.
Desktop automation capabilities include screenshot capture with configurable resolution scaling and flash suppression, keyboard and mouse input simulation, application launch and window management, UI element interaction and state retrieval, and DOM mode browser automation. System administration features cover file and directory management, Windows Registry access, clipboard read and write, process listing and termination, and PowerShell or system command execution. The server can be installed as a background or login task that starts automatically at system startup.
