MCP Connector

Control Computer Mouse, Keyboard, and Screen

A zero-dependency computer-use MCP server for mouse, keyboard, screenshots, and OCR via PyAutoGUI and RapidOCR.


91
Spark score
out of 100
Status Verified
Updated 6 months ago
Version 1.0.0
Models
universal

Add to Favorites

Why it matters

Automate desktop tasks by programmatically controlling your mouse, keyboard, and screen. This asset enables sophisticated OS-level automation for repetitive or complex user interactions.

Outcomes

What it gets done

01

Control mouse clicks and movements.

02

Simulate keyboard input and key presses.

03

Capture screenshots and extract text via OCR.

04

Manage and activate application windows.

Install

Add it to your toolbox

Run in your project directory:

curl -fsSL https://spark.entire.vc/get/vb-computer-control-mcp | bash

Capabilities

Tools your agent gets

click_screen

Click at specified screen coordinates

move_mouse

Move mouse cursor to specified coordinates

drag_mouse

Drag mouse from one position to another

mouse_down

Hold down a mouse button (left, right, middle)

mouse_up

Release a mouse button (left, right, middle)

type_text

Type specified text at current cursor position

press_key

Press specified key

key_down

Hold down a specific key until release

+7 tools

Overview

computer-control-mcp MCP Server

A zero-dependency computer-use MCP server for mouse, keyboard, screenshot, and OCR control, with Windows Graphics Capture for GPU-accelerated windows that otherwise screenshot as black. Use when an AI assistant needs direct desktop mouse/keyboard/screen control; run once via uvx before first MCP use to pre-download ~70MB of dependencies.

What it does

This MCP server provides computer control capabilities similar to Anthropic's "computer-use" - mouse, keyboard, screenshots, and OCR - built on PyAutoGUI, RapidOCR, and ONNXRuntime with zero external dependencies. Mouse control tools are click_screen(x, y), move_mouse(x, y), drag_mouse(from_x, from_y, to_x, to_y, duration=0.5), and mouse_down/mouse_up(button="left") for holding and releasing left/right/middle buttons. Keyboard tools are type_text(text), press_key(key), key_down/key_up(key) for holding a key until released, and press_keys(keys), which accepts single keys, sequences, or combinations. Screen and window tools include take_screenshot(...) (capture the full screen or a window matched by title pattern, with optional regex matching, OCR scaling, and saving to a downloads directory), take_screenshot_with_ocr(...) (the same capture, but also extracts and returns text with coordinates via OCR), get_screen_size(), list_windows(), activate_window(title_pattern, use_regex=False, threshold=60) to bring a matched window to the foreground, and wait_milliseconds(milliseconds).

Traditional screenshot methods (GDI/PrintWindow) fail on GPU-accelerated windows, producing black screens - this affects games, media players, Electron apps, GPU-accelerated browsers, streaming software, and CAD tools. The server addresses this with Windows Graphics Capture (WGC), triggerable via a flag on take_screenshot or automatically for windows matching configured title patterns.

When to use - and when NOT to

Use this when an AI assistant needs to directly control mouse, keyboard, and screen interactions on a desktop - clicking, typing, dragging, reading on-screen text via OCR, or managing windows.

The first run of uvx computer-control-mcp@latest downloads roughly 70MB of Python dependencies, which can take some time - running it once in a terminal before using it as an MCP server is recommended so that initial download doesn't happen mid-session. WGC-based screenshot capture is a Windows-specific feature; the black-screen GPU-window issue it solves is also Windows-specific (GDI/PrintWindow limitations).

Capabilities

Full mouse and keyboard control, screen/window screenshot capture (with optional OCR text-and-coordinate extraction), window listing and activation, and GPU-accelerated window capture via WGC on Windows - either invoked explicitly per call or automatically for windows matching configured title patterns.

How to install

Run directly via uvx computer-control-mcp@latest in an MCP client config, or install globally with pip install computer-control-mcp and run computer-control-mcp. The screenshot save location defaults to the OS downloads directory, customizable via the COMPUTER_CONTROL_MCP_SCREENSHOT_DIR environment variable (falling back to the default if the specified directory doesn't exist). Automatic WGC capture for specific windows is configured via COMPUTER_CONTROL_MCP_WGC_PATTERNS, a comma-separated list of window-title substrings (e.g. "obs, discord, game, steam") that trigger WGC automatically. The project is MIT-licensed.

Who it's for

Developers building AI agents that need direct desktop automation - clicking, typing, screenshot-based OCR, and window management - including reliable screenshot capture of GPU-accelerated applications on Windows.

{
  "mcpServers": {
    "computer-control-mcp": {
      "command": "uvx",
      "args": ["computer-control-mcp@latest"]
    }
  }
}
Source README

Computer Control MCP

MCP server that provides computer control capabilities, like mouse, keyboard, OCR, etc. using PyAutoGUI, RapidOCR, ONNXRuntime. Similar to 'computer-use' by Anthropic. With Zero External Dependencies.

Discord License: MIT PyPi

MCP Computer Control Demo

Quick Usage (MCP Setup Using uvx)

Note: Running uvx computer-control-mcp@latest for the first time will download python dependencies (around 70MB) which may take some time. Recommended to run this in a terminal before using it as MCP. Subsequent runs will be instant.

{
  "mcpServers": {
    "computer-control-mcp": {
      "command": "uvx",
      "args": ["computer-control-mcp@latest"]
    }
  }
}

OR install globally with pip:

pip install computer-control-mcp

Then run the server with:

computer-control-mcp # instead of uvx computer-control-mcp, so you can use the latest version, also you can `uv cache clean` to clear the cache and `uvx` again to use latest version.

Features

  • Control mouse movements and clicks
  • Type text at the current cursor position
  • Take screenshots of the entire screen or specific windows with optional saving to downloads directory
  • Extract text from screenshots using OCR (Optical Character Recognition)
  • List and activate windows
  • Press keyboard keys
  • Drag and drop operations
  • Enhanced screenshot capture for GPU-accelerated windows (Windows only)

Note on GPU-accelerated Windows

Traditional screenshot methods like GDI/PrintWindow fail to capture GPU-accelerated windows, resulting in black screens. This impacts games, media players, Electron apps, browsers with GPU acceleration, streaming software, and CAD tools. Use WGC through take_screenshot tool's flag or ENV variable

Configuration

Custom Screenshot Directory

By default, screenshots are saved to the OS downloads directory. You can customize this by setting the COMPUTER_CONTROL_MCP_SCREENSHOT_DIR environment variable:

{
  "mcpServers": {
    "computer-control-mcp": {
      "command": "uvx",
      "args": ["computer-control-mcp@latest"],
      "env": {
        "COMPUTER_CONTROL_MCP_SCREENSHOT_DIR": "C:\\Users\\YourName\\Pictures\\Screenshots"
      }
    }
  }
}

Or set it system-wide:

# Windows (PowerShell)
$env:COMPUTER_CONTROL_MCP_SCREENSHOT_DIR = "C:\Users\YourName\Pictures\Screenshots"

# macOS/Linux
export COMPUTER_CONTROL_MCP_SCREENSHOT_DIR="/home/yourname/Pictures/Screenshots"

If the specified directory doesn't exist, the server will fall back to the default downloads directory.

Automatic WGC for Specific Windows

You can configure the system to automatically use Windows Graphics Capture (WGC) for specific windows by setting the COMPUTER_CONTROL_MCP_WGC_PATTERNS environment variable. This variable should contain comma-separated patterns that match window titles:

{
  "mcpServers": {
    "computer-control-mcp": {
      "command": "uvx",
      "args": ["computer-control-mcp@latest"],
      "env": {
        "COMPUTER_CONTROL_MCP_WGC_PATTERNS": "obs, discord, game, steam"
      }
    }
  }
}

Or set it system-wide:

# Windows (PowerShell)
$env:COMPUTER_CONTROL_MCP_WGC_PATTERNS = "obs, discord, game, steam"

# macOS/Linux
export COMPUTER_CONTROL_MCP_WGC_PATTERNS="obs, discord, game, steam"

When this variable is set, any window whose title contains any of the specified patterns will automatically use WGC for screenshot capture, eliminating black screens for GPU-accelerated applications.

Available Tools

Mouse Control

  • click_screen(x: int, y: int): Click at specified screen coordinates
  • move_mouse(x: int, y: int): Move mouse cursor to specified coordinates
  • drag_mouse(from_x: int, from_y: int, to_x: int, to_y: int, duration: float = 0.5): Drag mouse from one position to another
  • mouse_down(button: str = "left"): Hold down a mouse button ('left', 'right', 'middle')
  • mouse_up(button: str = "left"): Release a mouse button ('left', 'right', 'middle')

Keyboard Control

  • type_text(text: str): Type the specified text at current cursor position
  • press_key(key: str): Press a specified keyboard key
  • key_down(key: str): Hold down a specific keyboard key until released
  • key_up(key: str): Release a specific keyboard key
  • press_keys(keys: Union[str, List[Union[str, List[str]]]]): Press keyboard keys (supports single keys, sequences, and combinations)

Screen and Window Management

  • take_screenshot(title_pattern: str = None, use_regex: bool = False, threshold: int = 60, scale_percent_for_ocr: int = None, save_to_downloads: bool = False, use_wgc: bool = False): Capture screen or window
  • take_screenshot_with_ocr(title_pattern: str = None, use_regex: bool = False, threshold: int = 10, scale_percent_for_ocr: int = None, save_to_downloads: bool = False): Extract adn return text with coordinates using OCR from screen or window
  • get_screen_size(): Get current screen resolution
  • list_windows(): List all open windows
  • activate_window(title_pattern: str, use_regex: bool = False, threshold: int = 60): Bring specified window to foreground
  • wait_milliseconds(milliseconds: int): Wait for a specified number of milliseconds

Development

Setting up the Development Environment

# Clone the repository
git clone https://github.com/AB498/computer-control-mcp.git
cd computer-control-mcp

# Build/Run:

# 1. Install in development mode | Meaning that your edits to source code will be reflected in the installed package.
pip install -e .

# Then Start server | This is equivalent to `uvx computer-control-mcp@latest` just the local code is used
computer-control-mcp

# -- OR --

# 2. Build after `pip install hatch` | This needs version increment in orer to reflect code changes
hatch build

# Windows
$latest = Get-ChildItem .\dist\*.whl | Sort-Object LastWriteTime -Descending | Select-Object -First 1
pip install $latest.FullName --upgrade 

# Non-windows
pip install dist/*.whl --upgrade

# Run
computer-control-mcp

Running Tests

python -m pytest

API Reference

See the API Reference for detailed information about the available functions and classes.

For more information or help

FAQ

Common questions

Trust

How it checks out

Official By maintainer
Downloads 0

Discussion

Questions & comments · 0

Sign In Sign in to leave a comment.