io.github.BorisGujvin/dittu MCP Server

This MCP server uses Dittu to turn an Android phone into an “eyes and hands” interface for AI assistants. A phone’s camera reads a monitor’s screen, while Bluetooth pairing provides real mouse and keyboard control, enabling remote visibility and interaction with a PC.

🛠️ Key Features

Camera-based viewing of a monitor for an AI assistant
Bluetooth-based mouse and keyboard input
Remote MCP endpoint: https://app.dittu.org/mcp (streamable-http)
Requires Authorization: Bearer <API_KEY>

🚀 Use Cases

Using an AI assistant to see what’s on a PC screen
Controlling a PC remotely without installing software on the target computer
Avoiding remote-desktop setup

⚡ Developer Benefits

Single remote MCP endpoint for integration
Setup paths referenced for Claude Desktop, Claude Code, Cursor, and ChatGPT

⚠️ Limitations

Uses Dittu hardware setup: a phone on a tripod facing a monitor
API key provisioning requires registering a device in the Dittu Android app

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.

Website: https://dittu.org

Setup instructions (Claude Desktop / Claude Code / Cursor / ChatGPT): https://dittu.org/setup

Remote MCP endpoint: https://app.dittu.org/mcp (streamable-http, Authorization: Bearer <API_KEY>)

Get an API key: register a device in the Dittu Android app — https://play.google.com/store/apps/details?id=com.dittu

Tools

Tool

What it does

Output

When to use

take_screenshot

Captures what the phone's camera currently sees on the monitor

Image

Before any action, to check current screen state

take_screenshot_with_grid

Same as take_screenshot but overlays a coordinate grid

Image

To locate exact click targets by coordinate

take_screenshot_with_crosshair(nx, ny)

Zoomed crop around a point with a crosshair marking the target

Image

To verify the cursor will land exactly where intended, before clicking a small/important target

get_raw_screenshot

Unprocessed camera frame, no corner-mapping applied

Image

Debugging camera alignment issues

move_mouse(nx, ny)

Moves the cursor to a normalized screen coordinate without clicking

Confirmation

Positioning the cursor before a verified click

click(nx, ny)

Left-clicks at a normalized screen coordinate

Confirmation

Standard click actions

double_click(nx, ny)

Double left-clicks at a normalized screen coordinate

Confirmation

Opening files/apps, other double-click actions

scroll

Scrolls the screen in a given direction

Confirmation

Navigating long pages or lists

key

Sends a keyboard key or shortcut

Confirmation

Shortcuts, Enter, Escape, arrow keys, etc.

type_text

Types a string of text via the Bluetooth keyboard

Confirmation

Filling in text fields, search boxes, documents

get_corners

Reads the current four-corner monitor calibration

Coordinates

Diagnosing why clicks land off-target

set_corners

Sets the four-corner monitor calibration

Confirmation

Fixing calibration when the camera view is misaligned or cropped

Install

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://app.dittu.org/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "dittu": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://app.dittu.org/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

io.github.BorisGujvin/dittu