qt-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| QT_MCP_HOST | No | Probe TCP host (used by the MCP server to connect to the probe). | localhost |
| QT_MCP_PORT | No | Probe TCP listen port. | 9142 |
| QT_MCP_PROBE | No | Set to 1 to auto-activate the probe in the target application. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| qt_snapshotA | Capture the full Qt widget tree as a structured accessibility-like snapshot. Returns a YAML-like text tree with widget types, object names, text content, geometry, visibility, enabled state, and interaction refs (w1, w2, ...). Use the refs to interact with specific widgets via other tools. |
| qt_screenshotA | Take a screenshot of the entire window or a specific widget. |
| qt_widget_detailsA | Get detailed properties of a specific widget. |
| qt_clickB | Click a widget. |
| qt_typeB | Type text into a widget. |
| qt_key_pressA | Send a key event to a widget or the focused widget. |
| qt_set_propertyB | Set a Qt property on a widget. |
| qt_invoke_slotB | Invoke a slot or method on a QObject. |
| qt_get_textA | Extract text content from a text editor or input widget. |
| qt_trigger_actionA | Trigger a menu action or toolbar action by text or index. |
| qt_wait_forA | Wait for a UI state change. |
| qt_list_windowsB | List all top-level windows and their types. |
| qt_object_treeB | Get the full QObject parent-child tree (not just visible widgets). |
| qt_active_popupB | Check for active popup or modal dialog widgets. |
| qt_menu_itemsC | Get actions from a QMenu widget. |
| qt_messagesB | Returns all console messages |
| qt_thread_checkA | Check thread affinity of all QObjects to detect threading issues. Reports which threads own QObjects, flags QWidget subclasses on non-GUI threads (the #1 cause of GUI freezes), and lists QThread instances. |
| qt_signalsA | Inspect signal connections on a QObject. |
| qt_layout_checkA | Detect layout issues in the visible widget tree. |
| qt_scene_snapshotC | Get all items in a QGraphicsScene. |
| qt_vtk_scene_infoB | Get VTK scene state from a PyVista/VTK widget. |
| qt_vtk_screenshotC | Capture a VTK render window to an image. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 22 tools
Most tools have distinct purposes, but some overlap exists: qt_screenshot and qt_vtk_screenshot both capture images, and qt_snapshot and qt_object_tree both provide widget tree information, though they differ in scope (visible vs. full tree). The descriptions help clarify these distinctions, but an agent might occasionally confuse them.
All tools follow a consistent 'qt_' prefix with snake_case naming, using clear verb_noun patterns (e.g., qt_click, qt_get_text, qt_list_windows). This predictability makes it easy for agents to understand and navigate the toolset.
With 22 tools, the count feels heavy for a UI testing/automation server, potentially overwhelming for agents. While the tools cover various aspects (interaction, inspection, debugging), it might benefit from consolidation or better categorization to reduce cognitive load.
The toolset comprehensively covers the domain of Qt application testing and debugging, including widget interaction (click, type), inspection (snapshot, details), debugging (signals, threads), and specialized features (VTK, screenshots). No obvious gaps are present; agents can perform full workflows from discovery to validation.