dittu
Turns a phone into a camera+Bluetooth remote so AI assistants can see and control any PC.
我該用這個嗎
品質與安全性
發現項目（4）
- LOWTool 'click' description lacks action verb在 click 中
- LOWTool 'double_click' description lacks action verb在 double_click 中
- LOWTool 'key' description lacks action verb在 key 中
- LOWTool 'scroll' description lacks action verb在 scroll 中
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"dittu": {
"url": "https://app.dittu.org/mcp"
}
}
}遠端端點
https://app.dittu.org/mcpstreamable-http它能做什麼
工具清單
工具（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.
輸入結構描述
{
"type": "object",
"properties": {},
"title": "take_screenshotArguments"
}⚪take_screenshot_with_grid(step)
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.
輸入結構描述
{
"type": "object",
"properties": {
"step": {
"default": 0.1,
"title": "Step",
"type": "number"
}
},
"title": "take_screenshot_with_gridArguments"
}🟢take_screenshot_with_crosshair(nx, ny, zoom)
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).
輸入結構描述
{
"type": "object",
"properties": {
"nx": {
"title": "Nx",
"type": "number"
},
"ny": {
"title": "Ny",
"type": "number"
},
"zoom": {
"default": 4,
"title": "Zoom",
"type": "number"
}
},
"required": [
"nx",
"ny"
],
"title": "take_screenshot_with_crosshairArguments"
}🟢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.
輸入結構描述
{
"type": "object",
"properties": {},
"title": "get_raw_screenshotArguments"
}🟢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.
輸入結構描述
{
"type": "object",
"properties": {},
"title": "get_cornersArguments"
}🟡set_corners(tl, tr, br, bl)
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.
輸入結構描述
{
"type": "object",
"properties": {
"tl": {
"items": {
"type": "number"
},
"title": "Tl",
"type": "array"
},
"tr": {
"items": {
"type": "number"
},
"title": "Tr",
"type": "array"
},
"br": {
"items": {
"type": "number"
},
"title": "Br",
"type": "array"
},
"bl": {
"items": {
"type": "number"
},
"title": "Bl",
"type": "array"
}
},
"required": [
"tl",
"tr",
"br",
"bl"
],
"title": "set_cornersArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "set_cornersOutput"
}⚪move_mouse(nx, ny)
Move mouse cursor to normalized coordinates WITHOUT clicking. nx, ny: float 0.0000–1.0000.
輸入結構描述
{
"type": "object",
"properties": {
"nx": {
"title": "Nx",
"type": "number"
},
"ny": {
"title": "Ny",
"type": "number"
}
},
"required": [
"nx",
"ny"
],
"title": "move_mouseArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "move_mouseOutput"
}⚪click(nx, ny)
Click at normalized screen coordinates. nx, ny: float 0.0000–1.0000 where (0,0) = top-left, (1,1) = bottom-right.
輸入結構描述
{
"type": "object",
"properties": {
"nx": {
"title": "Nx",
"type": "number"
},
"ny": {
"title": "Ny",
"type": "number"
}
},
"required": [
"nx",
"ny"
],
"title": "clickArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "clickOutput"
}⚪double_click(nx, ny)
Double-click at normalized screen coordinates.
輸入結構描述
{
"type": "object",
"properties": {
"nx": {
"title": "Nx",
"type": "number"
},
"ny": {
"title": "Ny",
"type": "number"
}
},
"required": [
"nx",
"ny"
],
"title": "double_clickArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "double_clickOutput"
}⚪type_text(text)
Type text on the computer keyboard.
輸入結構描述
{
"type": "object",
"properties": {
"text": {
"title": "Text",
"type": "string"
}
},
"required": [
"text"
],
"title": "type_textArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "type_textOutput"
}⚪key(modifiers, keycodes)
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])
輸入結構描述
{
"type": "object",
"properties": {
"modifiers": {
"title": "Modifiers",
"type": "integer"
},
"keycodes": {
"items": {
"type": "integer"
},
"title": "Keycodes",
"type": "array"
}
},
"required": [
"modifiers",
"keycodes"
],
"title": "keyArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "keyOutput"
}⚪scroll(delta)
Scroll the mouse wheel. delta: number of ticks. Positive = scroll down, negative = scroll up.
輸入結構描述
{
"type": "object",
"properties": {
"delta": {
"title": "Delta",
"type": "integer"
}
},
"required": [
"delta"
],
"title": "scrollArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "scrollOutput"
}社群
證據