MCP servers and skills: search, filter by where they run, and compare.
Extract false-positive and false-negative gaps from VLM binary-classification-question (BCQ, yes/no) predictions. Use when the user asks to "analyze VLM BCQ gaps", "extract VLM false positives and fal
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Run predictions with a finetuned KERMT checkpoint on a SMILES-only CSV. The skill validates that the input ckpt has task FFN heads (refuses pretrain ckpts with a redirect to kermt-finetune), validates
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Run TAO Data Services object-detection gap analysis from ground-truth and inference annotations. Use when an object detection workflow needs to identify weak images by comparing model predictions agai
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Manages Agent Platform serving endpoints. Use when you need to create, list, describe, update, or delete serving endpoints for model deployment on Agent Platform. Also use when troubleshooting endpoin
OfficialSkillApache-2.0★ 21k in collectionNo key
Find NOAA tide stations and NDBC buoys, fetch tide predictions, water levels, tidal currents, and live buoy conditions via MCP. STDIO or Streamable HTTP.
Node.jsApache-2.0★ 1Few starsNo key
Run TAO Data Services KPI analysis for object detection, comparing inference annotations against ground truth to compute per-class TP/FP/FN/TN, precision, recall, accuracy, and AP at a fixed IoU. Use
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Performs deep Root Cause Analysis (RCA) on NVIDIA TAO Visual ChangeNet classification experiments with image-evidence-driven investigation. Use when analyzing ChangeNet model failures, investigating p
OfficialSkillApache-2.0★ 3.6k in collectionNo key
One person, a team of agents: CLI, Web, Desktop & Python SDK with multi-session collaboration, persistent memory, and self-evolving skills. 一个人，一支 Agent 团队：支持多终端协作、持久记忆与技能自进化的 AI Agent 框架。
PythonApache-2.0★ 357No key
Bring DataRobot platform capabilities to your coding agents
SkillApache-2.0★ 31No key
AI-queryable MCP server for unified real-time air, sea, and space tracking — 25+ tools, agent skills, guardrails, and a 3D globe
PythonApache-2.0★ 18No key
Enterprise Model Context Protocol (MCP) server for live and historical sports analytics, odds, and predictions via ESPN
PythonApache-2.0Few starsNo key
Predict which files AI coding agents will miss — implementation spike + compiler + reference graph
GoApache-2.0★ 4Few starsNo key
ARVX connector for AI agents: run ARVX Readings from any MCP-compatible assistant. Keeps nothing.
Hosted by authorApache-2.0Few starsNo key
Validate coding-sequence CSVs, extract public CodonFM/Encodon embeddings, and choose checkpoints for downstream property modeling.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Adapt BOP datasets, run the FoundationPose perception pipeline with TAO depth, and evaluate or re-score pose results. Use for dataset runs and result comparisons; environment installation belongs to f
OfficialSkillApache-2.0★ 3.6k in collectionNo key
A research-stage registry where AI agents file falsifiable claims about systemic problems and run open-weights ensembles against them. Disagreement between models is the output
Node.jsApache-2.0★ 2Few starsNo key
Who stands behind it
