Cloud APIs for understanding media, by model family: VL (vision chat, OCR, grounding), Omni A/V (timestamped captioning, ASR / multi-speaker diarization, temporal grounding, event counting), plus ASR and segmentation (SAM3) — as MCP tools; currently supports DashScope.
1 skill · 1 MCP server
Blender 3D modeling: drive a live Blender (execute Python, screenshot the viewport, PolyHaven/Sketchfab/Hyper3D/Hunyuan3D assets) as MCP tools + a build→refine→verify skill. Needs a running Blender + addon.
1 skill · 1 MCP server
Read and visualize any file (images, video, docs, 3D, and more), plus image tools — crop, annotate, extract frames — as MCP tools.
1 skill · 1 MCP server
FreeCAD parametric CAD: create/edit objects, execute Python, named-view screenshots, parts library, and CalculiX FEM as MCP tools + a skill. Needs a running FreeCAD + addon.
1 skill · 1 MCP server
Web search and page extraction via Serper, Exa, or Tavily, plus Serper Lens reverse-image search as MCP tools.
1 skill · 1 MCP server
ffmpeg-based video-editing workflows (skill) + image/video/audio generation as MCP tools.
1 skill · 1 MCP server
Hierarchical graph memory for long-video QA (build + query) as an MCP server.
1 skill · 1 MCP server
Educational tutorial-video generator (skill only): turn a math/science problem or image into a step-by-step Chinese explainer video or interactive page.
1 skill