MCP servers and skills: search, filter by where they run, and compare.
3D content in Remotion using Three.js and React Three Fiber.
OfficialInstructionsApache-2.0★ 19k in collectionNo key
NVPanoptix3D for panoptic 3D scene reconstruction from posed RGB images. Produces 3D panoptic segmentation (semantic, instance, and panoptic masks) with occupancy completion. Built on a VGGT backbone
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Deploy and operate the RTVI-CV-3D microservice as MV3DT (`MODE=mv3dt`): per-camera DeepStream perception plus BEV Fusion over calibrated cameras. Supports the bundled sample dataset, custom video file
OfficialSkillApache-2.0★ 3.6k in collectionNo key
React Three Fiber 3D renderer for json-render. Use when working with @json-render/react-three-fiber, building 3D scenes from JSON specs, rendering meshes/lights/models/environments, or integrating Thr
OfficialSkillApache-2.0★ 19k in collectionNo key
Sparse4D for multi-camera temporal 3D object detection and tracking. Uses sparse queries with deformable attention across camera views and time for end-to-end 3D perception, with an instance bank for
OfficialSkillApache-2.0★ 3.6k in collectionNo key
BEVFusion for multi-sensor 3D object detection. Fuses LiDAR point clouds and camera images in bird's-eye-view (BEV) space, used in autonomous driving for robust 3D perception. Use when training, evalu
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Run and operate the DeepStream Multi-View 3D Tracking reference app, also known as MV3DT. Use when the user asks to set up prerequisites, run shipped MV3DT samples, run Multi-View 3D Tracking on custo
OfficialSkillCC-BY-4.0 AND Apache-2.0★ 3.6k in collectionNo key
Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
PointPillars for 3D object detection from LiDAR point clouds. Encodes point clouds into a pseudo-image via a pillar-based representation, then applies 2D detection — used in autonomous driving and rob
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Authoring and debugging scripts for Rhinoceros 3D (Rhino 8 and later). Use when asked to write RhinoScript (VBScript / .rvb / .vbs), RhinoPython, or RhinoCommon-based scripts; automate Rhino modeling
OfficialSkillMIT★ 40k in collectionNo key
Expert skill for building web-based game engines and games using HTML5, Canvas, WebGL, and JavaScript. Use when asked to create games, build game engines, implement game physics, handle collision dete
in the skill textstarter templates, reference documentation, and step-by-step workflows for 2D and 3D game development with frameworks such as Phaser, Three.js, Babylon.js, and A-Frame. ## When
OfficialSkillMIT★ 40k in collectionNo key
Stereo depth estimation using FoundationStereo. Predicts disparity maps from stereo image pairs for 3D reconstruction. Use when training, evaluating, exporting, or running inference for a TAO Foundati
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Expert skill for writing FreeCAD Python scripts, macros, and automation. Use when asked to create FreeCAD models, parametric objects, Part/Mesh/Sketcher scripts, workbench tools, GUI dialogs with PySi
in the skill textFreeCAD CAD application. Interprets shorthand, quasi-code, and natural language descriptions of 3D modeling tasks and translates them into correct FreeCAD Python API calls. ## When
OfficialSkillMIT★ 40k in collectionNo key
The Generative UI framework
in the skill textinstall @json-render/core @json-render/react @json-render/next # or for 3D scenes (and gaussian splatting via the GaussianSplat component) npm install @json-render/core
OfficialSkillApache-2.0★ 19kNo key
Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.
in the skill textthe Python qdrant_client (PointStruct) with id, payload (e.g., color), and a 3D-like vector for similarity search. It supports parallel uploads (parallel=4) and
OfficialSkillMIT★ 40k in collectionNo key
Run NV-Reason-CT inference on user-provided 3D NIfTI chest or abdominal CT volumes for engineering and research workflows. Not for diagnosis, treatment, or clinical reporting.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Best practices for Remotion - Video creation in React
in the skill textuse Read individual rule files for detailed explanations and code examples: - rules/3d.md - 3D content in Remotion using Three.js and React Three Fiber - rules/animations.md - Fundamental animation skills
OfficialSkillApache-2.0★ 19k in collectionNo key
Qdrant provides client SDKs for various programming languages, allowing easy integration with Qdrant deployments.
in the skill textthe Python qdrant_client (PointStruct) with id, payload (e.g., color), and a 3D-like vector for similarity search. It supports parallel uploads (parallel=4) and
OfficialSkillApache-2.0★ 256 in collectionNo key
Router for NVIDIA NuRec/NRE: USDZ rendering, NCore conversion, 3DGS, gRPC sensor sim, carline adaptation, PhysicalAI HF datasets. Do NOT use for SimReady or infra setup.
in the skill textrecordings — typically from a self-driving car or a robot — into a 3D scene that can be re-rendered from any viewpoint. A typical project runs
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use as the top-level router for Omniverse Realtime Viewer USD app requests and focused viewer reference documents.
in the skill textreview evidence before handoff. ## Non-Negotiables - Use `ovrtx` for all USD and 3D rendering. - Browser apps display an `ovstream` WebRTC video stream plus UI. The browser
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Use to deploy the vss-behavior-analytics service standalone (entrypoint, config-source, optional calibration). Not for the full warehouse deploy.
in the skill textthe full stack" - "Change the entrypoint to fusion_search / dev_example / analytics 3D / mv3dt" - "Use my own behavior-analytics config / calibration JSON" - "Point behavior-analytics
OfficialSkillApache-2.0★ 3.6k in collectionNo key
A collection of Model Context Protocol (MCP) servers, clients and developer tools by IBM.
in the readme2Fhost.docker.internal%3A8500%22%2C%22-e%22%2C%22CONSUL_HTTP_TOKEN%3D%24%7BCONSUL_DC1_TOKEN%7D%22%2C%22hashicorp%2Fconsul-mcp-server
OfficialSkillApache-2.0★ 413No key
Who stands behind it
Who stands behind it
