Desktop Automation
Enables desktop automation with RobotJS for screen capture, keyboard input, and mouse control, allowing direct interaction with de
MCP Desktop Automation is a server that provides desktop automation capabilities using RobotJS and screenshot functionality, enabling AI assistants to control mouse movements, keyboard inputs, and capture screenshots. Developed by Adriano Bonat, the implementation exposes tools for screen capture, keyboard/mouse control, and screen size detection through a standardized interface that works with various MCP clients but is primarily tested with Claude Desktop. The server handles system-level permissions for screen capture and input simulation, making it valuable for users who want their AI assistant to interact directly with desktop applications without manual intervention.
Source
Repository: https://github.com/tanob/mcp-desktop-automation
Maintain Desktop Automation?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[Desktop Automation on getagentictools](https://getagentictools.com/mcp/tanob-mcp-desktop-automation?ref=badge) Related mcp
OpenSTAAD MCP server for Bentley STAAD.Pro structural analysis software via the OpenSTAAD API.
AgentGate Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve.
Kage Persistent memory for coding agents — store, retrieve, and query project context across sessions.
Prismatic Prism Local MCP server that wraps Prismatic's Prism CLI tool for code-native integration and custom component development.
Meta-Prompting Transforms language models into dynamic multi-agent systems where the model alternates between a Conductor role that breaks down c
Roslyn CodeLens Roslyn-based semantic code intelligence for .NET codebases with type hierarchy, call graph, and dependency injection analysis.