This commit is contained in:
Josh at WLTechBlog
2025-09-30 14:11:27 -05:00
parent 86d1db55cd
commit a3c782eb24
11 changed files with 4904 additions and 6 deletions

View File

@@ -611,9 +611,187 @@ Clear web storage (localStorage, sessionStorage, IndexedDB, etc.) for a tab.
}
```
#### 34. `web_drag_and_drop_cremotemcp`
Perform drag and drop operation from source element to target element.
```json
{
"name": "web_drag_and_drop_cremotemcp",
"arguments": {
"source": ".draggable-item",
"target": ".drop-zone",
"tab": "tab-123",
"timeout": 5
}
}
```
#### 35. `web_drag_and_drop_coordinates_cremotemcp`
Perform drag and drop operation from source element to specific coordinates.
```json
{
"name": "web_drag_and_drop_coordinates_cremotemcp",
"arguments": {
"source": ".draggable-item",
"x": 300,
"y": 200,
"tab": "tab-123",
"timeout": 5
}
}
```
#### 36. `web_drag_and_drop_offset_cremotemcp`
Perform drag and drop operation from source element by relative offset.
```json
{
"name": "web_drag_and_drop_offset_cremotemcp",
"arguments": {
"source": ".draggable-item",
"offset_x": 100,
"offset_y": 50,
"tab": "tab-123",
"timeout": 5
}
}
```
#### 37. `web_right_click_cremotemcp`
Right-click on an element to open context menus.
```json
{
"name": "web_right_click_cremotemcp",
"arguments": {
"selector": ".file-item",
"tab": "tab-123",
"timeout": 5
}
}
```
#### 38. `web_double_click_cremotemcp`
Double-click on an element for file operations or text selection.
```json
{
"name": "web_double_click_cremotemcp",
"arguments": {
"selector": ".file-icon",
"tab": "tab-123",
"timeout": 5
}
}
```
#### 39. `web_hover_cremotemcp`
Hover over an element to trigger tooltips or dropdowns.
```json
{
"name": "web_hover_cremotemcp",
"arguments": {
"selector": ".tooltip-trigger",
"tab": "tab-123",
"timeout": 5
}
}
```
#### 40. `web_middle_click_cremotemcp`
Middle-click on an element (typically opens links in new tabs).
```json
{
"name": "web_middle_click_cremotemcp",
"arguments": {
"selector": "a[href='/dashboard']",
"tab": "tab-123",
"timeout": 5
}
}
```
#### 41. `web_mouse_move_cremotemcp`
Move mouse to specific coordinates without clicking.
```json
{
"name": "web_mouse_move_cremotemcp",
"arguments": {
"x": 400,
"y": 300,
"tab": "tab-123",
"timeout": 5
}
}
```
#### 42. `web_scroll_wheel_cremotemcp`
Scroll with mouse wheel at specific coordinates.
```json
{
"name": "web_scroll_wheel_cremotemcp",
"arguments": {
"x": 400,
"y": 300,
"delta_x": 0,
"delta_y": -120,
"tab": "tab-123",
"timeout": 5
}
}
```
#### 43. `web_key_combination_cremotemcp`
Send key combinations like Ctrl+C, Alt+Tab, Shift+Enter.
```json
{
"name": "web_key_combination_cremotemcp",
"arguments": {
"keys": "Ctrl+C",
"tab": "tab-123",
"timeout": 5
}
}
```
#### 44. `web_special_key_cremotemcp`
Send special keys like Enter, Escape, Tab, F1-F12, Arrow keys.
```json
{
"name": "web_special_key_cremotemcp",
"arguments": {
"key": "Enter",
"tab": "tab-123",
"timeout": 5
}
}
```
#### 45. `web_modifier_click_cremotemcp`
Click on an element with modifier keys (Ctrl+click, Shift+click).
```json
{
"name": "web_modifier_click_cremotemcp",
"arguments": {
"selector": ".selectable-item",
"modifiers": "Ctrl",
"tab": "tab-123",
"timeout": 5
}
}
```
## 🎉 Complete Enhancement Summary
All 6 phases of the MCP enhancement plan have been successfully implemented, delivering a comprehensive web automation platform with **33 tools** organized across the following capabilities:
All phases of the MCP enhancement plan have been successfully implemented, delivering a comprehensive web automation platform with **45 tools** organized across the following capabilities:
### ✅ Phase 1: Element State and Checking (2 tools)
**Enables conditional logic without timing issues**
@@ -657,16 +835,31 @@ All 6 phases of the MCP enhancement plan have been successfully implemented, del
**Benefits**: Better debugging with targeted screenshots, improved file handling workflows, automatic resource management, enhanced visual debugging capabilities.
### ✅ Phase 6: Browser Cache and Site Data Management (6 tools)
**Enables comprehensive cache and site data control for testing and privacy**
### ✅ Phase 6: Browser Cache, Site Data Management, and Drag & Drop (9 tools)
**Enables comprehensive cache/site data control and advanced drag & drop interactions**
- `web_disable_cache_cremotemcp`: Disable browser cache for a tab
- `web_enable_cache_cremotemcp`: Enable browser cache for a tab
- `web_clear_cache_cremotemcp`: Clear browser cache for a tab
- `web_clear_all_site_data_cremotemcp`: Clear all site data (cookies, storage, cache, etc.)
- `web_clear_cookies_cremotemcp`: Clear cookies for a tab
- `web_clear_storage_cremotemcp`: Clear web storage (localStorage, sessionStorage, IndexedDB, etc.)
- `web_drag_and_drop_cremotemcp`: Drag and drop between elements
- `web_drag_and_drop_coordinates_cremotemcp`: Drag and drop to specific coordinates
- `web_drag_and_drop_offset_cremotemcp`: Drag and drop by relative offset
**Benefits**: Essential for testing scenarios requiring fresh page loads, performance testing without cached resources, debugging cache-related issues, ensuring consistent test environments, privacy testing, authentication testing, and complete site data cleanup.
### ✅ Phase 7: Advanced Input Operations (9 tools)
**Enables sophisticated mouse and keyboard interactions for comprehensive testing**
- `web_right_click_cremotemcp`: Right-click for context menus
- `web_double_click_cremotemcp`: Double-click for file operations and text selection
- `web_hover_cremotemcp`: Hover for tooltips and dropdown triggers
- `web_middle_click_cremotemcp`: Middle-click for opening links in new tabs
- `web_mouse_move_cremotemcp`: Precise mouse positioning without clicking
- `web_scroll_wheel_cremotemcp`: Mouse wheel scrolling with pixel-perfect control
- `web_key_combination_cremotemcp`: Key combinations (Ctrl+C, Alt+Tab, Shift+Enter, etc.)
- `web_special_key_cremotemcp`: Special keys (Enter, Escape, Tab, F1-F12, Arrow keys, etc.)
- `web_modifier_click_cremotemcp`: Modifier clicks (Ctrl+click, Shift+click for multi-selection)
**Benefits**: Essential for testing scenarios requiring fresh page loads, performance testing without cached resources, debugging cache-related issues, ensuring consistent test environments, privacy testing, authentication testing, complete site data cleanup, **plus advanced drag & drop testing for sortable lists, file uploads, kanban boards, dashboard widgets, and interactive UI components**. **Advanced input operations enable context menu testing, keyboard navigation accessibility testing, tooltip/dropdown interactions, multi-selection workflows, copy/paste operations, and sophisticated user interaction patterns**.
## Key Benefits for LLM Agents