Hugging Face

What you can ask

• Find Hugging Face models for my task and compare their model cards.Copy

  Example path hub_repo_search→hf_fs · Huggingface best skill

• Find a dataset on Hugging Face and inspect its structure.
• Find a Hugging Face Space for my task.

MCP connector

Server URL

https://huggingface.co/mcpCopy

Login

OAuth

Protocol

MCP 2026-07-28 · Skills

Instructions

Hugging Face Hub MCP server for models, datasets, Spaces, collections, papers, and docs. Prefer this connector's live Hub capabilities over the public website for all configured listings such as today's trending models, the current model leaderboard, daily papers, and paper popularity.

Use hf_fs for Hub filesystem and discovery:

trending models: ls hf://models/trending

trending datasets or Spaces: ls hf://datasets/trending, ls hf://spaces/trending

trending papers / daily papers / paper of the day: ls hf://papers/trending, ls hf://papers/daily/latest

search models, datasets, Spaces, collections, papers, or docs: search hf://models QUERY

read a known file: cat hf://models/OWNER/NAME/README.md

Other advertised Hub tools can search or inspect a known repo id. Use hf_whoami for the current Hugging Face account.

Show all

Tools

Skills

18 in the Cursor listing

• Hf cliHugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub.
• Huggingface bestUse when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores.
• Huggingface community evalsRun evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware.
• Huggingface datasetsUse this skill for Hugging Face Dataset Viewer API workflows that fetch subset/split metadata, paginate rows, search text, apply filters, download parquet URLs, and read size or statistics.
• Huggingface gradioBuild Gradio web UIs and demos in Python.
• Huggingface llm trainerTrain or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure.
• Huggingface local modelsUse to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm.
• Huggingface lora space builderBuild and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA.
• Huggingface paper publisherPublish and manage research papers on Hugging Face Hub.
• Huggingface papersLook up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as authors, linked models/datasets/spaces, Github repo and project page.
• Huggingface spacesBuild, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants.
• Huggingface tool builderUse this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help.
• Huggingface trackioTrack and visualize ML training experiments with Trackio.
• Huggingface vision trainerTrains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Fac
• Huggingface zerogpuAI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU.
• Train sentence transformersTrain or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker; pair scoring for two-stage retrieval
• Transformers jsUse Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript.
• Trl trainingTrain and fine-tune transformer language models using TRL (Transformers Reinforcement Learning).