native-devtools-mcp 0.4.3 → 0.4.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +4 -1
- package/package.json +3 -3
package/README.md
CHANGED
|
@@ -54,7 +54,8 @@ This MCP server is designed to be **highly discoverable and usable** by AI model
|
|
|
54
54
|
1. `take_screenshot`: The "eyes". Returns images + layout metadata + text locations (OCR).
|
|
55
55
|
2. `click` / `type_text`: The "hands". Interacts with the system based on visual feedback.
|
|
56
56
|
3. `find_text`: A shortcut to find text on screen and get its coordinates immediately. Uses the platform **accessibility API** (macOS Accessibility / Windows UI Automation) for precise element-level matching, with OCR fallback.
|
|
57
|
-
4. `
|
|
57
|
+
4. `element_at_point`: Inspect the accessibility element at given screen coordinates — returns name, role, label, value, bounds, pid, and app_name. Note: privacy-focused Electron apps (e.g. Signal) may restrict their AX tree, returning only a container — use `take_screenshot` with OCR as a fallback.
|
|
58
|
+
5. `load_image` / `find_image`: Template matching for non-text UI elements (icons, shapes), returning screen coordinates for clicking.
|
|
58
59
|
|
|
59
60
|
## 📦 Installation
|
|
60
61
|
|
|
@@ -317,10 +318,12 @@ graph TD
|
|
|
317
318
|
| **macOS** | Screenshots | `screencapture` (CLI) |
|
|
318
319
|
| | Input | `CGEvent` (CoreGraphics) |
|
|
319
320
|
| | Text Search (`find_text`) | `Accessibility API` (primary), Vision OCR (fallback) |
|
|
321
|
+
| | Element Inspection (`element_at_point`) | `AXUIElementCopyElementAtPosition` + AX tree walk fallback (Accessibility API) |
|
|
320
322
|
| | OCR | `VNRecognizeTextRequest` (Vision Framework) |
|
|
321
323
|
| **Windows** | Screenshots | `BitBlt` (GDI) |
|
|
322
324
|
| | Input | `SendInput` (Win32) |
|
|
323
325
|
| | Text Search (`find_text`) | `UI Automation` (primary), WinRT OCR (fallback) |
|
|
326
|
+
| | Element Inspection (`element_at_point`) | `IUIAutomation::ElementFromPoint` (UI Automation) |
|
|
324
327
|
| | OCR | `Windows.Media.Ocr` (WinRT) |
|
|
325
328
|
| **Android** | Screenshots | `screencap` / ADB framebuffer |
|
|
326
329
|
| | Input | `adb shell input` (tap, swipe, text, keyevent) |
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "native-devtools-mcp",
|
|
3
|
-
"version": "0.4.
|
|
3
|
+
"version": "0.4.4",
|
|
4
4
|
"mcpName": "io.github.sh3ll3x3c/native-devtools",
|
|
5
5
|
"description": "MCP server for native app testing — screenshot, OCR, click, type, find_text, template matching. macOS, Windows & Android.",
|
|
6
6
|
"license": "MIT",
|
|
@@ -53,8 +53,8 @@
|
|
|
53
53
|
"bin"
|
|
54
54
|
],
|
|
55
55
|
"optionalDependencies": {
|
|
56
|
-
"@sh3ll3x3c/native-devtools-mcp-darwin-arm64": "0.4.
|
|
57
|
-
"@sh3ll3x3c/native-devtools-mcp-win32-x64": "0.4.
|
|
56
|
+
"@sh3ll3x3c/native-devtools-mcp-darwin-arm64": "0.4.4",
|
|
57
|
+
"@sh3ll3x3c/native-devtools-mcp-win32-x64": "0.4.4"
|
|
58
58
|
},
|
|
59
59
|
"engines": {
|
|
60
60
|
"node": ">=18"
|