MCP Server

dittu

io.github.BorisGujvin/dittu
IoT & Hardware Productivity Public & reachable MCP 2025-11-25

What this MCP does

Uses a phone camera to view and calibrate a computer screen and remotely control it with mouse, keyboard, scrolling, and text input.

click
Click at normalized screen coordinates. nx, ny: float 0.0000–1.0000 where (0,0) = top-left, (1,1) = bottom-right.
Input schema
{'type': 'object', 'title': 'clickArguments', 'required': ['nx', 'ny'], 'properties': {'nx': {'type': 'number', 'title': 'Nx'}, 'ny': {'type': 'number', 'title': 'Ny'}}}
Output schema
{'type': 'object', 'title': 'clickOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
double_click
Double-click at normalized screen coordinates.
Input schema
{'type': 'object', 'title': 'double_clickArguments', 'required': ['nx', 'ny'], 'properties': {'nx': {'type': 'number', 'title': 'Nx'}, 'ny': {'type': 'number', 'title': 'Ny'}}}
Output schema
{'type': 'object', 'title': 'double_clickOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
get_corners
Get the phone's current screen-corner calibration. Returns {"tl": [nx,ny], "tr": [nx,ny], "br": [nx,ny], "bl": [nx,ny]} — each corner is a normalized point (0.0–1.0) in the RAW camera frame, defining the perspective warp that maps the camera view onto a flat rectangle representing the monitor. These four points are an arbitrary quadrilateral (trapezoid), not a bounding box — adjust one corner at a time without assuming the others move symmetrically.
Input schema
{'type': 'object', 'title': 'get_cornersArguments', 'properties': {}}
get_raw_screenshot
Capture the RAW camera frame — no perspective warp, no crop to the calibrated screen quad. Use this to see exactly what the camera sees before any correction, e.g. when troubleshooting why take_screenshot looks wrong, or before adjusting corners with get_corners/set_corners.
Input schema
{'type': 'object', 'title': 'get_raw_screenshotArguments', 'properties': {}}
key
Press a key combination. modifiers bitmask: LCtrl=1, LShift=2, LAlt=4, LWin=8 Common keycodes: Enter=40, Escape=41, Tab=43, Space=44, F4=61, PageDown=78, PageUp=75, Win=227 Examples: Alt+F4 → key(4, [61]) Ctrl+W → key(1, [26])
Input schema
{'type': 'object', 'title': 'keyArguments', 'required': ['modifiers', 'keycodes'], 'properties': {'keycodes': {'type': 'array', 'items': {'type': 'integer'}, 'title': 'Keycodes'}, 'modifiers': {'type': 'integer', 'title': 'Modifiers'}}}
Output schema
{'type': 'object', 'title': 'keyOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
move_mouse
Move mouse cursor to normalized coordinates WITHOUT clicking. nx, ny: float 0.0000–1.0000.
Input schema
{'type': 'object', 'title': 'move_mouseArguments', 'required': ['nx', 'ny'], 'properties': {'nx': {'type': 'number', 'title': 'Nx'}, 'ny': {'type': 'number', 'title': 'Ny'}}}
Output schema
{'type': 'object', 'title': 'move_mouseOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
scroll
Scroll the mouse wheel. delta: number of ticks. Positive = scroll down, negative = scroll up.
Input schema
{'type': 'object', 'title': 'scrollArguments', 'required': ['delta'], 'properties': {'delta': {'type': 'integer', 'title': 'Delta'}}}
Output schema
{'type': 'object', 'title': 'scrollOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
set_corners
Update the phone's screen-corner calibration. Each corner is [nx, ny] normalized 0.0–1.0 in the raw camera frame. tl/tr/br/bl = top-left/top-right/bottom-right/bottom-left of the monitor as seen by the camera (an arbitrary trapezoid due to perspective — not a rectangle). Call get_corners() first to read the current values before nudging one of them.
Input schema
{'type': 'object', 'title': 'set_cornersArguments', 'required': ['tl', 'tr', 'br', 'bl'], 'properties': {'bl': {'type': 'array', 'items': {'type': 'number'}, 'title': 'Bl'}, 'br': {'type': 'array', 'items': {'type': 'number'}, 'title': 'Br'}, 'tl': {'type': 'array', 'items': {'type': 'number'}, 'title': 'Tl'}, 'tr': {'type': 'array', 'items': {'type': 'number'}, 'title': 'Tr'}}}
Output schema
{'type': 'object', 'title': 'set_cornersOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
take_screenshot
Capture the current screen via the Dittu phone camera. Returns a JPEG image. Call this to see what's on screen before acting.
Input schema
{'type': 'object', 'title': 'take_screenshotArguments', 'properties': {}}
take_screenshot_with_crosshair
Capture the screen, crop tightly around (nx, ny), zoom in, and draw a crosshair at exactly that expected position. Use this for screen-corner calibration: move_mouse(nx, ny) near a screen edge, then call this to see whether the actual cursor lines up with the crosshair (where it SHOULD be if calibration is perfect). If the cursor is offset from the crosshair, or missing entirely (edge is cropped out of frame), corners need adjusting — see get_corners/set_corners. nx, ny: the same coordinates you passed to move_mouse. zoom: magnification factor for the cropped region (default 4x).
Input schema
{'type': 'object', 'title': 'take_screenshot_with_crosshairArguments', 'required': ['nx', 'ny'], 'properties': {'nx': {'type': 'number', 'title': 'Nx'}, 'ny': {'type': 'number', 'title': 'Ny'}, 'zoom': {'type': 'number', 'title': 'Zoom', 'default': 4.0}}}
take_screenshot_with_grid
Capture the screen and overlay a coordinate grid. step: grid spacing (default 0.1, use 0.05 for finer grid on small UI elements). Returns a JPEG image with grid drawn on top.
Input schema
{'type': 'object', 'title': 'take_screenshot_with_gridArguments', 'properties': {'step': {'type': 'number', 'title': 'Step', 'default': 0.1}}}
type_text
Type text on the computer keyboard.
Input schema
{'type': 'object', 'title': 'type_textArguments', 'required': ['text'], 'properties': {'text': {'type': 'string', 'title': 'Text'}}}
Output schema
{'type': 'object', 'title': 'type_textOutput', 'required': ['result'], 'properties': {'result': {'type': 'string', 'title': 'Result'}}}
Added
scroll
Sept. 17, 2026, 12:40 p.m.
Added
key
Sept. 17, 2026, 12:40 p.m.
Added
type_text
Sept. 17, 2026, 12:40 p.m.
Added
double_click
Sept. 17, 2026, 12:40 p.m.
Added
click
Sept. 17, 2026, 12:40 p.m.
Added
move_mouse
Sept. 17, 2026, 12:40 p.m.
Added
set_corners
Sept. 17, 2026, 12:40 p.m.
Added
get_corners
Sept. 17, 2026, 12:40 p.m.
Added
get_raw_screenshot
Sept. 17, 2026, 12:40 p.m.
Added
take_screenshot_with_crosshair
Sept. 17, 2026, 12:40 p.m.
Added
take_screenshot_with_grid
Sept. 17, 2026, 12:40 p.m.
Added
take_screenshot
Sept. 17, 2026, 12:40 p.m.