Dittu

io.github.BorisGujvinPublished by GitHub account BorisGujvinv1.0.0Updated Oct 24, 2026

Turns a phone into a camera+Bluetooth remote so AI assistants can see and control any PC.

VerifiedStreamable HTTPWeb executableBrowser AutomationDeveloper Tools

Overview

AI-generated overview

Dittu lets an AI assistant see a PC monitor through a phone camera and control the computer via Bluetooth mouse and keyboard.

What you can do
Capture the monitor view through the phone camera, with plain, grid-overlay, zoomed crosshair, or raw unprocessed frames for locating targets and debugging alignment. Move the cursor, click, double-click and scroll at normalized screen coordinates. Type text and send key combinations through the paired Bluetooth keyboard. Read and update the four-corner monitor calibration that maps the camera view onto the screen.
When to use it
Useful when an assistant should operate a computer that cannot have software installed, or when no remote-desktop setup is available and a phone can be placed facing the monitor. Suited to repetitive desktop tasks and on-screen actions rather than description alone.
Requirements
The remote streamable-HTTP endpoint, an API key obtained by registering a device in the Dittu Android app, and an Android phone on a tripod facing the monitor with Bluetooth paired to the target computer. Network access is needed.
Before you install
The endpoint requires a bearer API key, which should be kept secret. The assistant can click, type, send shortcuts and change calibration on the target computer, so unintended actions are possible; verify targets with screenshots before acting. Camera images of the screen are sent to the Dittu service.

Installation

In SourceWeft

  1. Open Dittu in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.BorisGujvin%2Fdittu/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "dittu": {
      "type": "http",
      "url": "https://app.dittu.org/mcp"
    }
  }
}

README

Dittu MCP Server

Dittu turns a phone into the eyes and hands of an AI assistant. Stand the phone on a tripod facing a monitor — the camera reads the screen, Bluetooth pairs as a real mouse and keyboard. No software to install on the target computer, no remote-desktop setup.

Tools

ToolWhat it doesOutputWhen to use
take_screenshotCaptures what the phone's camera currently sees on the monitorImageBefore any action, to check current screen state
take_screenshot_with_gridSame as take_screenshot but overlays a coordinate gridImageTo locate exact click targets by coordinate
take_screenshot_with_crosshair(nx, ny)Zoomed crop around a point with a crosshair marking the targetImageTo verify the cursor will land exactly where intended, before clicking a small/important target
get_raw_screenshotUnprocessed camera frame, no corner-mapping appliedImageDebugging camera alignment issues
move_mouse(nx, ny)Moves the cursor to a normalized screen coordinate without clickingConfirmationPositioning the cursor before a verified click
click(nx, ny)Left-clicks at a normalized screen coordinateConfirmationStandard click actions
double_click(nx, ny)Double left-clicks at a normalized screen coordinateConfirmationOpening files/apps, other double-click actions
scrollScrolls the screen in a given directionConfirmationNavigating long pages or lists
keySends a keyboard key or shortcutConfirmationShortcuts, Enter, Escape, arrow keys, etc.
type_textTypes a string of text via the Bluetooth keyboardConfirmationFilling in text fields, search boxes, documents
get_cornersReads the current four-corner monitor calibrationCoordinatesDiagnosing why clicks land off-target
set_cornersSets the four-corner monitor calibrationConfirmationFixing calibration when the camera view is misaligned or cropped

Why a camera instead of screen-sharing?

Because it works on any computer — no software to install, no permissions to configure, no remote-desktop setup. If the monitor is in front of the phone, an AI assistant can see it and control it.

Built for

  • Automating repetitive desktop tasks
  • Controlling a computer you can't install anything on
  • Letting an AI assistant actually do things on-screen, not just describe them

Source: README.md at commit faa17eb

Tools

12

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.

Takes no parameters.

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.

Parametersstep

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).

Parametersnxrequirednyrequiredzoom

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.

Takes no parameters.

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.

Takes no parameters.

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.

Parametersblrequiredbrrequiredtlrequiredtrrequired

move_mouse

Move mouse cursor to normalized coordinates WITHOUT clicking. nx, ny: float 0.0000–1.0000.

Parametersnxrequirednyrequired

click

Click at normalized screen coordinates. nx, ny: float 0.0000–1.0000 where (0,0) = top-left, (1,1) = bottom-right.

Parametersnxrequirednyrequired

double_click

Double-click at normalized screen coordinates.

Parametersnxrequirednyrequired

type_text

Type text on the computer keyboard.

Parameterstextrequired

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])

Parameterskeycodesrequiredmodifiersrequired

scroll

Scroll the mouse wheel. delta: number of ticks. Positive = scroll down, negative = scroll up.

Parametersdeltarequired

Version history

1
  1. v1.0.0LatestSep 16, 2026

Score

90% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.