jiayan-xu/dsh-nuphus-mcp
Desktop and browser automation bridge (36 tools): window/screen/mouse/keyboard control with PaddleOCR element perception, Chrome CDP browsing with accessibility snapshots.
Listed
0
Tools
Bundle verified
What it does
Desktop and browser automation bridge (36 tools): window/screen/mouse/keyboard control with PaddleOCR element perception, Chrome CDP browsing with accessibility snapshots.
Best for
- Windows desktop automation requiring real window, screen, mouse, keyboard, or clipboard control.
- Local UI workflows that benefit from PaddleOCR element perception and optional YOLO icon detection.
- Chrome automation needing CDP navigation, interaction, scripted sequences, and accessibility snapshots.
- Visual inspection workflows with an available OpenAI-compatible vision endpoint.
Not ideal for
- Environments without an accessible `nuphus-mcp.exe`; the built-in executable path is Windows-specific.
- Workflows that cannot tolerate actions affecting the real mouse, keyboard, clipboard, or operating-system windows.
- Browser environments without Chrome CDP access.
- Users expecting vision analysis without configuring both the required API key and model.
README
dsh-nuphus-mcp
dsh-nuphus-mcp bridges dsh to the nuphus MCP server for desktop and browser automation. It registers 36 statically described tools: 15 desktop_* tools and 21 browser_* tools.
Capabilities
Desktop tools cover:
- Screen dimensions and full-screen or regional screenshots.
- Listing, activating, inspecting, moving, resizing, and capturing windows.
- Mouse clicks, movement, hovering, scrolling, and dragging.
- Keyboard input and hotkeys.
- Clipboard writing and clearing.
- Local UI element perception with PaddleOCR and optional YOLO icon detection.
- Optional screenshot analysis through a user-configured OpenAI-compatible vision endpoint.
Browser tools use Chrome CDP and include navigation, interaction, scripted multi-step operations, and accessibility-tree snapshots. Snapshot results assign references such as @1 to interactive elements for later click or input operations, with DOM traversal as a fallback when the accessibility tree is unavailable.
Runtime Configuration
The plugin runs nuphus-mcp.exe as a persistent stdio MCP child process. Requests use newline-delimited JSON-RPC, concurrent calls are matched by request ID, and a later call reconnects after the child process exits.
Set NUPHUS_EXE to override the executable path. The built-in default is:
%USERPROFILE%\.qclaw\workspace\nuphus-mcp\target\debug\nuphus-mcp.exe
Optional vision analysis requires both:
NUPHUS_MCP_VISION_API_KEYNUPHUS_MCP_VISION_MODEL
Plugin logs are appended to ~/.dsh/logs/dsh-nuphus-mcp.log when the path is writable.
Safety
Desktop actions affect the real mouse, keyboard, clipboard, and operating-system windows. Browser automation can execute JavaScript. Operations classified as writes expose a confirm parameter that must be true when nuphus runs in strict-confirm mode.
The dsh bundle registers @jhp830901/dsh-nuphus-mcp with the ID dsh-nuphus-mcp.
Frequently Asked QuestionsFAQ
Use the verified command dsh plugin --profile default add github:jiayan-xu/dsh-nuphus-mcp in a DSH-enabled shell. The command resolves the public package metadata and keeps the plugin attached to the catalog identity shown on this page.
Compatibility follows the bundle and profile status shown above. If a profile is not detected, keep the plugin disabled there and check the repository documentation before enabling it in production.
The GitHub link and activity metadata are the source of truth for releases and maintenance. Revisit this page after a new release to confirm the catalog has observed the latest version.