Skip to content

io.github.BorisGujvin/dittu

by BorisGujvin · remote · no sign-in to list tools · v1.0.0 · published by GitHub user BorisGujvin

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

Final · 4Changes · 7
CompareRegistry entry

12 tools: 4 do something that can't be undone, 7 change things and 1 only read.

Scanned Oct 21, 2026

No check matched anything in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http dittu https://app.dittu.org/mcp

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

12 tools

Can't be undone 4Claude Code: ask
  • get_raw_screenshotCapture the RAW camera frame — no perspective warp, no crop to the calibrated screen quad.No findings

    Why it is in this group

    • The name "get_raw_screenshot" says "get": a word for reading.
    • The description's first verb is "capture": a word that usually means money moves, which cannot be taken back.
    Description, as the server wrote it
    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.
  • take_screenshotCapture the current screen via the Dittu phone camera.No findings

    Why it is in this group

    • The name "take_screenshot" says "screenshot": a word for reading.
    • The description's first verb is "capture": a word that usually means money moves, which cannot be taken back.
    Description, as the server wrote it
    Capture the current screen via the Dittu phone camera. Returns a JPEG image. Call this to see what's on screen before acting.
  • take_screenshot_with_crosshairCapture the screen, crop tightly around (nx, ny), zoom in, and draw a crosshair at exactly that expected position.No findings

    Why it is in this group

    • The name "take_screenshot_with_crosshair" says "screenshot": a word for reading.
    • The description's first verb is "capture": a word that usually means money moves, which cannot be taken back.
    Description, as the server wrote it
    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).
  • take_screenshot_with_gridCapture the screen and overlay a coordinate grid.No findings

    Why it is in this group

    • The name "take_screenshot_with_grid" says "screenshot": a word for reading.
    • The description's first verb is "capture": a word that usually means money moves, which cannot be taken back.
    Description, as the server wrote it
    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.
Changes things 7Claude Code: ask
  • clickClick at normalized screen coordinates.No findings

    Why it is in this group

    • The name "click" says "click": a word for a change.
    Description, as the server wrote it
    Click at normalized screen coordinates. nx, ny: float 0.0000–1.0000 where (0,0) = top-left, (1,1) = bottom-right.
  • double_clickDouble-click at normalized screen coordinates.No findings

    Why it is in this group

    • The name "double_click" says "click": a word for a change.
    Description, as the server wrote it
    Double-click at normalized screen coordinates.
  • keyPress a key combination.No findings

    Why it is in this group

    • The description's first verb is "press": a word for a change.
    Description, as the server wrote it
    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])
  • move_mouseMove mouse cursor to normalized coordinates WITHOUT clicking.No findings

    Why it is in this group

    • The name "move_mouse" says "move": a word for a change.
    Description, as the server wrote it
    Move mouse cursor to normalized coordinates WITHOUT clicking. nx, ny: float 0.0000–1.0000.
  • scrollScroll the mouse wheel.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    Description, as the server wrote it
    Scroll the mouse wheel. delta: number of ticks. Positive = scroll down, negative = scroll up.
  • set_cornersUpdate the phone's screen-corner calibration.No findings

    Why it is in this group

    • The name "set_corners" says "set": a word for a change.
    Description, as the server wrote it
    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.
  • type_textType text on the computer keyboard.No findings

    Why it is in this group

    • The name "type_text" says "type": a word for a change.
    Description, as the server wrote it
    Type text on the computer keyboard.
Only reads 1Claude Code: allow
  • get_cornersGet the phone's current screen-corner calibration.No findings

    Why it is in this group

    • The name "get_corners" says "get": a word for reading.
    Description, as the server wrote it
    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.

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.0.0. Values in angle brackets are yours to fill in.

claude mcp add --transport http dittu https://app.dittu.org/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__dittu__get_corners"
    ],
    "ask": [
      "mcp__dittu__take_screenshot",
      "mcp__dittu__take_screenshot_with_grid",
      "mcp__dittu__take_screenshot_with_crosshair",
      "mcp__dittu__get_raw_screenshot",
      "mcp__dittu__set_corners",
      "mcp__dittu__move_mouse",
      "mcp__dittu__click",
      "mcp__dittu__double_click",
      "mcp__dittu__type_text",
      "mcp__dittu__key",
      "mcp__dittu__scroll"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as dittu. Review it before you use it.