Skip to content
Agentmart
Submit a tool

Screen Control

Safety-gated computer use for AI agents: screen OCR and vision, mouse, keyboard, window control.

Connector by Xeakaes · GitHub account verified by the MCP Registry

IndexedMIT★ 4
Write a review

Install

Pick your client. Read the repository before you give any tool access to your data.

No install instructions from the source yet. Check the repository for setup steps.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Safety-gated computer use for AI agents: screen OCR and vision, mouse, keyboard, window control.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list, install config and code. Checked Oct 26, 2026.

Tools
8 read · 3 write · 0 delete · 5 not yet classified
Secrets
None asked for
Install scripts
None found

Tools by what they do 16

Read from the source code; the running server may list different tools.

Read 8 · Look things up without changing anything.

  • get_held
  • get_info
  • list_windows
  • ocr_screen
  • screenshot
  • window_capture_ocr
  • window_children
  • window_input_mode

Write 3 · Create, change, send or run things.

  • close_window
  • release_all
  • window_post

Not yet classified 5 · We could not tell from the name and description.

  • focus_window
  • game
  • keyboard
  • motion_diff
  • mouse

Network hosts it talks to 1

  • github.com · found in code

Files it touches

  • /dev/uinput
  • /tmp/sc-linux-test.jpg
  • Your home directory (~)
  • ~/Desktop
  • ~/Documents
  • ~/OneDrive/Desktop
  • ~/OneDrive/Documents

Tools (16)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • close_window

    Close a window safely (WM_CLOSE after verification — never blind Alt+F4). Pass expect_title/expect_process to refuse (409) if the window changed.

  • focus_window

    Bring a window to the foreground (focus it).

  • game

    Game mode for FPS-style control. action: start (clip cursor to center) | move (relative camera look by dx,dy pixels * sensitivity) | stop | heartbeat (keep-alive during long holds). Combine with keyboard() down/up for WASD and mouse(action='down'/'up') for shooting/building.

  • get_held

    List currently held keys/buttons and watchdog status.

  • get_info

    Server/PC status: screen size, monitors, OCR availability, failsafe and game-mode state.

  • keyboard

    Control the keyboard. action: press | hotkey | type | down | up. press: key name (enter, f11, a...); hotkey: keys=["ctrl","s"]; type: Unicode-safe text. expect_hwnd refuses (409) the action if the foreground window differs — use it to avoid typing into the wrong app.

  • list_windows

    List visible top-level windows: hwnd, title, process name, pid.

  • motion_diff

    Text-only change detection between two snapshots: which tiles of the screen changed and their clickable centers. Use to verify an action had an effect or to spot movement without OCR/vision.

  • mouse

    Control the mouse. action: move | click | scroll | drag | down | up. click uses x,y (optional = current pos); drag goes (x1,y1)->(x,y); scroll uses 'clicks' (negative = down). Physical-pixel coordinates.

  • ocr_screen

    Read the screen as text with coordinates (OCR). Best for menus, dialogs, editors, chat — anything text-heavy. Returns lines plus per-item centers for clicking. 'region' is an optional "x,y,w,h" crop.

  • release_all

    Release every held key and button (emergency reset). Safe to call anytime.

  • screenshot

    Capture the screen as an image (for vision-capable models). 'region' = "x,y,w,h"; 'scale' 0-1 shrinks to save bandwidth; 'quality' 1-100.

  • window_capture_ocr

    Capture a background window WITHOUT focusing it; with ocr=1 (default) returns its text directly — read other apps' content while the user works.

  • window_children

    List child controls of a window (class name, title, hwnd). Useful for classic Win32 apps with real child controls (e.g. an Edit box) — target the child hwnd in window_post. Modern WinUI/UWP apps have no classic children; use window_input_mode to detect them.

  • window_input_mode

    Classify how a window receives input BEFORE posting to it: postmessage (classic Win32) | uia (WinUI/UWP: focus+SendInput fallback) | focused (already foreground) | invalid (dead window).

Show 1 more tools
  • window_post

    Send input to a window in the background. action: type | key | hotkey | click | scroll. mode: auto (recommended — routes WinUI/UWP apps through the focused SendInput path automatically) | background | focused. Note: 'uia' routing focuses the window (unavoidable for modern apps).

Signals

Stars
4
Forks
0
Open issues
0
Last commit
Oct 18, 2026 (10 days ago)
Last release
Sep 17, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.Xeakaes/computer-use-for-all-agents
Version
1.0.0
License
MIT
Repository
github.com/Xeakaes/computer-use-for-all-agents
Website
github.com/Xeakaes/computer-use-for-all-agents
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

Screen Control MCP server. Agent Mart. https://agentmart.dev/connectors/xeakaes-computer-use-for-all-agents (last updated 2026-10-24)