MCP server

Dittu

io.github.BorisGujvin/dittu

Checked 25 Oct 2026, 20:29 UTC · Connected to it and listed its tools

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

Website Source

At a glance

Type

MCP server

Publisher

Not verified

Status

Working at last check

Tools

12

Token cost

About 1,542 tokens per request

Sets up in

Claude Code, Claude Desktop, Codex, Gemini CLI, Cursor, VS Code, Antigravity, ChatGPT, OpenAI API, Grok

Last checked

25 Oct 2026, 20:29 UTC

Connect it to your agent

Add to CursorAdd to VS CodeVS Code Insiders

Opens the app, which shows the server and asks you to confirm. For other apps, copy the setup below.

Claude Code

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

Claude Desktop

Settings → Connectors → Add custom connector, and paste the URL.

Codex (config.toml)

[mcp_servers.dittu]
url = "https://app.dittu.org/mcp"

Gemini CLI

{"mcpServers":{"dittu":{"httpUrl":"https://app.dittu.org/mcp"}}}

Cursor

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

VS Code

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

Antigravity

agy mcp add dittu https://app.dittu.org/mcp

ChatGPT

Settings → Apps & Connectors → Advanced settings: turn on Developer mode, then Create a connector and paste the URL. Which plans can do this varies.

OpenAI API (Responses tools)

{"type":"mcp","server_label":"dittu","server_url":"https://app.dittu.org/mcp","require_approval":"always"}

Grok (xAI API tools)

{"type":"mcp","server_label":"dittu","server_url":"https://app.dittu.org/mcp"}

Tools

• click Browses the web · ~95 tokens
  Click at normalized screen coordinates. nx, ny: float 0.0000–1.0000 where (0,0) = top-left, (1,1) = bottom-right.
• double_click Browses the web · ~75 tokens
  Double-click at normalized screen coordinates.
• get_corners ~177 tokens
  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 t
• get_raw_screenshot ~125 tokens
  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.
• key ~154 tokens
  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_mouse ~91 tokens
  Move mouse cursor to normalized coordinates WITHOUT clicking. nx, ny: float 0.0000–1.0000.
• scroll ~81 tokens
  Scroll the mouse wheel. delta: number of ticks. Positive = scroll down, negative = scroll up.
• set_corners ~223 tokens
  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 ge
• take_screenshot Browses the web · ~77 tokens
  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_crosshair Browses the web · ~270 tokens
  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 i
• take_screenshot_with_grid Browses the web · ~114 tokens
  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.
• type_text ~60 tokens
  Type text on the computer keyboard.

Browse

• GitHub tools
• Video meetings
• GitHub and code hosting

Related MCP servers

• Apuchat
  Real-time chat for AI agents. Claude Code, Cursor, Cline and Codex join channels over MCP.
• LTX-2-LoRAs-Camera-Control-Dolly
  Camera Control Dolly Distilled
• LTX-2-LoRAs-Camera-Control-Dolly
  Camera Control Dolly Distilled
• SMI Aware Assistant
  Remote MCP server exposing SMI Aware tools, resources, and skills over Streamable HTTP.
• Fibo Edit Multi-Angle Control
  Control camera angles with Fibo Edit and Multi-Angle LoRA
• HardwareMCP
  Find MCP servers for ESP32, Arduino, 3D printers, Home Assistant, cameras and other hardware.
• SANA-WM Camera-Controlled World Model
  Image-to-video with 6-DoF camera control.
• oriiion
  Your marketing, a message away

Badge for your README

[![AptLynx](https://aptlynx.net/badge/io.github.BorisGujvin/dittu.svg)](https://aptlynx.net/servers/io.github.BorisGujvin/dittu)

Listing text is written by the maker; AptLynx lists tools and does not vouch for them. Find another tool · Browse by topic · For agents