{
  "markdown": "# Dittu MCP Server\n\nDittu turns a phone into the eyes and hands of an AI assistant. Stand the phone on a tripod\nfacing a monitor — the camera reads the screen, Bluetooth pairs as a real mouse and keyboard.\nNo software to install on the target computer, no remote-desktop setup.\n\n- Website: https://dittu.org\n- Setup instructions (Claude Desktop / Claude Code / Cursor / ChatGPT): https://dittu.org/setup\n- Remote MCP endpoint: `https://app.dittu.org/mcp` (streamable-http, `Authorization: Bearer <API_KEY>`)\n- Get an API key: register a device in the Dittu Android app — https://play.google.com/store/apps/details?id=com.dittu\n\n## Tools\n\n| Tool | What it does | Output | When to use |\n|---|---|---|---|\n| `take_screenshot` | Captures what the phone's camera currently sees on the monitor | Image | Before any action, to check current screen state |\n| `take_screenshot_with_grid` | Same as `take_screenshot` but overlays a coordinate grid | Image | To locate exact click targets by coordinate |\n| `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 |\n| `get_raw_screenshot` | Unprocessed camera frame, no corner-mapping applied | Image | Debugging camera alignment issues |\n| `move_mouse(nx, ny)` | Moves the cursor to a normalized screen coordinate without clicking | Confirmation | Positioning the cursor before a verified click |\n| `click(nx, ny)` | Left-clicks at a normalized screen coordinate | Confirmation | Standard click actions |\n| `double_click(nx, ny)` | Double left-clicks at a normalized screen coordinate | Confirmation | Opening files/apps, other double-click actions |\n| `scroll` | Scrolls the screen in a given direction | Confirmation | Navigating long pages or lists |\n| `key` | Sends a keyboard key or shortcut | Confirmation | Shortcuts, Enter, Escape, arrow keys, etc. |\n| `type_text` | Types a string of text via the Bluetooth keyboard | Confirmation | Filling in text fields, search boxes, documents |\n| `get_corners` | Reads the current four-corner monitor calibration | Coordinates | Diagnosing why clicks land off-target |\n| `set_corners` | Sets the four-corner monitor calibration | Confirmation | Fixing calibration when the camera view is misaligned or cropped |\n\n## Why a camera instead of screen-sharing?\n\nBecause it works on any computer — no software to install, no permissions to configure, no\nremote-desktop setup. If the monitor is in front of the phone, an AI assistant can see it and\ncontrol it.\n\n## Built for\n\n- Automating repetitive desktop tasks\n- Controlling a computer you can't install anything on\n- Letting an AI assistant actually do things on-screen, not just describe them\n",
  "bytes": 2783,
  "sha": "d6e424efea381ce825529ce8954bcb75ac313b4771f5462dbe735ed057936a3b",
  "repo_slug": "borisgujvin/dittu-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_borisgujvin_dittu_33a89b77/readme"
}