M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
M

MCPControl

Community
Windows desktop automation server for AI models
How to install ↓ Compare GitHub source repository ↗
Category
Dev Tools #315 of 438
Stars
★ 330 Popular
Transport
SSE
Runtime
Node.js 18+ · Python
Credentials
No credential needed
License
MIT
Last commit
⚠

Static review · not runListed 2026-08-07

FMRS 44/100 · D · Weakest Security and permissions 6/20 — Read the FMRS scoring method →

Fit and risk

What it can accessRuns commands or code

Best for

  • Developers and testers who want to delegate Windows desktop automation to AI in a controlled environment
  • Researchers and AI experimenters needing programmatic desktop control
  • Users building AI agents that require visual feedback

Not for

  • Non-Windows systems (Windows only)
  • Multi-monitor or non-standard resolutions requiring high click accuracy
  • Production environments with high security requirements without proper safeguards

Required permissions

  • Mouse control
  • Keyboard control
  • Window management
  • Screen capture
  • Clipboard access

Risks and side effects

  • This software is experimental and may cause unintended consequences.
  • Direct control of mouse and keyboard can lead to unintended actions or data loss.
  • HTTPS is mandatory for remote deployments to avoid interception.
  • Some operations may require elevated permissions.

Setup

Before you start

Runtime：Node.js 18+ · Python

Other optional settings (6)
AUTOMATION_PROVIDER optional Sets the global automation provider (keysender/powershell/autohotkey); defaults to keysender, optional.
AUTOHOTKEY_PATH optional Path to the AutoHotkey v2 executable, needed only if it is not in PATH.
AUTOMATION_KEYBOARD_PROVIDER optional Provider override for keyboard operations, optional.
AUTOMATION_MOUSE_PROVIDER optional Provider override for mouse operations, optional.
AUTOMATION_SCREEN_PROVIDER optional Provider override for screen operations, optional.
AUTOMATION_CLIPBOARD_PROVIDER optional Provider override for clipboard operations, optional.
  1. Install Visual Studio 2022 Build Tools (including VC++ workload).
  2. Install Python 3.12 (required for node-gyp).
  3. Install Node.js (latest LTS).
  4. Install MCPControl globally: npm install -g mcp-control.
  5. Start the server with SSE transport: mcp-control --sse.
  6. Configure your client with the SSE URL (e.g., http://192.168.1.100:3232/mcp).

Check that it works

After configuring the SSE connection, restart the Claude client and MCPControl should appear in the MCP menu; asking 'list all open windows' should return a window list, confirming the connection.

Troubleshooting

  1. Ensure Visual Studio Build Tools and Python are installed for native modules.
  2. Check that the server is running with SSE mode and the network port is accessible.
  3. For remote access, use HTTPS with valid TLS certificates.
  4. Verify the URL in the client configuration is correct.
  5. Review known limitations, such as unsupported minimize/restore and get_screenshot not working in Cline.

Things to try

Once connected, you can ask your AI assistant things like:

  • Move the active window to the top-left corner and resize it to 800x600
  • Type the text hello into Notepad and press Enter
  • Take a screenshot of the current screen and tell me what it shows
  • List all open windows and tell me which one is active

Use cases

Delegate repetitive UI testing to AI
Automate workflows and form filling
AI gaming and visual reasoning experiments
Cross-application integration and demo creation

Overview

MCPControl is an MCP server for Windows OS automation, providing programmatic control over mouse, keyboard, window management, and screen capture. It bridges AI models with your desktop, enabling secure control of mouse movements, clicks, keyboard input, window operations, screenshots, and clipboard. It supports Windows only and recommends a virtual machine at 1280x720 resolution for optimal performance.

Similar servers

Context7 80 · B

Upstash's official server providing up-to-date third-party library docs for AI coding assistants

★ 62.9k · Tools 2 Compare with this →
Compare with other MCP servers

Source revision f90024255aa6 Data synced 2026-10-12 Read the FMRS scoring method