Omniscient Master Suite OMNISCIENT · 3.1

Screenshotter v1.0.0

Clipboard & system screenshotter 3 actions MCP

Capture a full screenshot of any display or a precise pixel region, saved as a timestamped PNG to a folder of your choice.

The omniscient:// link needs a protocol handler on your machine, which is not built yet. Until then it does nothing — use the commands below.

Actions

Jump to: list_displayscapture_screencapture_region

List displays

list_displays

List the available displays with their index, position and size, so you know what to pass as 'display' to capture_screen.

Inputs

This action takes no inputs.

Outputs

NameTypeNotes
displays json

Capture a screen

capture_screen

Capture a whole display and save it as a PNG. display 0 captures every display combined (the full virtual desktop); 1, 2, ... capture one physical display (see list_displays).

Inputs

NameTypeRequired / defaultValues and notes
out path optional, default ""
display int optional, default 0
prefix string optional, default screenshot

Outputs

NameTypeNotes
file path
width int
height int

Capture a region

capture_region

Capture a rectangular pixel region of the desktop (x, y, width, height, in absolute desktop coordinates) and save it as a PNG.

Inputs

NameTypeRequired / defaultValues and notes
x int required
y int required
w int required
h int required
out path optional, default ""
prefix string optional, default screenshot

Outputs

NameTypeNotes
file path
width int
height int

Use it

List displays

Command line

shell
python app.py --action list_displays --params '{}'

Run from the app’s own folder. Single quotes work in bash and PowerShell; in cmd.exe use double quotes and escape the inner ones.

MCP tool

mcp
run_action("screenshotter", "list_displays", {})

Workflow node

json
{
  "id": "n0",
  "app": "screenshotter",
  "action": "list_displays",
  "params": {},
  "inputs": {}
}

Capture a screen

Command line

shell
python app.py --action capture_screen --params '{}'

Run from the app’s own folder. Single quotes work in bash and PowerShell; in cmd.exe use double quotes and escape the inner ones.

MCP tool

mcp
run_action("screenshotter", "capture_screen", {})

Workflow node

json
{
  "id": "n0",
  "app": "screenshotter",
  "action": "capture_screen",
  "params": {},
  "inputs": {}
}

Capture a region

Command line

shell
python app.py --action capture_region --params '{"x": 1, "y": 1, "w": 1, "h": 1}'

Run from the app’s own folder. Single quotes work in bash and PowerShell; in cmd.exe use double quotes and escape the inner ones.

MCP tool

mcp
run_action("screenshotter", "capture_region", {"x": 1, "y": 1, "w": 1, "h": 1})

Workflow node

json
{
  "id": "n0",
  "app": "screenshotter",
  "action": "capture_region",
  "params": {
    "x": 1,
    "y": 1,
    "w": 1,
    "h": 1
  },
  "inputs": {}
}

Example prompts

Things you can say to Claude, Cursor or Codex once the MCP server is registered.