"Traditional Welsh Dish Cawl" matching MCP servers:

Enables agent-native desktop control by driving mouse, keyboard, and interface elements through accessibility-first semantic operations, with fallback to screen coordinates when accessibility cannot reach a target.

Enables safe Windows desktop automation and computer use through natural language, including window observation, UI Automation, and execution of verified actions like clicking, typing, and scrolling.

Enables AI assistants to check disk usage on the host machine, providing real-time reports on partition health, warnings, and critical alerts across Windows, macOS, and Linux.

Windows computer-use MCP server: accessibility-first element actions (UIA), UI read as diffed text trees instead of screenshots, guarded raw input, and a cross-session arbiter that yields to the human. 19 tools.

Lets an agent install, control, and repair dsh web as a Windows service so it auto-starts at boot, runs without a console window, and survives sign-out — covering service status, install/uninstall, start/stop/restart, and a side-effect-free install preview. It also tails service logs and translates them into plain-language diagnoses with fixes for failures like port conflicts, incompatible profile plugins, and plugin trees that fail to load.

MCP stdio server that lets DSH agents see and operate Windows desktop apps via UI Automation, screenshots, mouse/keyboard, OCR, and window management.

Provides desktop automation capabilities (e.g., click, browser snapshot) as MCP tools for DSH agents, enabling computer use via natural language.

Enables AI agents to observe and control the user's live desktop by listing apps, reading accessibility trees, and performing clicks, typing, scrolling, dragging, and other input actions with per-action approvals and local audit archives.

Enables models to enumerate and diagnose OpenSSH host aliases, run remote commands or shell scripts, transfer files safely, manage remote processes, and perform non-interactive privilege checks/operations within strict safety boundaries.

Enables the model to observe and control the live desktop via accessibility trees and screenshots, performing actions like clicking, typing, scrolling, dragging, and setting values.