mcp-windows
View on GitHubLet AI agents control Windows applications. Click buttons, type text, toggle settings — all by name, not coordinates. Uses the Windows UI Automation API to find UI elements reliably, regardless of DPI, theme, resolution, or window position.
An MCP server and CLI for controlling Windows applications through the Windows UI Automation API. Agents can inspect controls and click, type, select, and read by element identity, with screenshot and coordinate input as a fallback.
Use Cases
Let AI agents operate Windows applicationsAutomate desktop workflows by accessible control namesInteract with dialogs, forms, menus, and tablesAutomate browser pages through UI Automation and ARIA labelsUse screenshot and coordinate input for custom controls
Built With
- Language
- C#
- Frameworks
- .NET 10 · Windows UI Automation
Tags
Windows automation · UI Automation · desktop control · semantic selectors · keyboard input · mouse input · screenshots · MCP server · CLI · RPA · Windows 10 · Windows 11