AI. MCP servers, the command line and skills for connecting an agent to Hugging Face.
Official server
1 server
Sourced servers by others
6
Command line
hf
Vendor skills
26
Official server
Published by Hugging Face's owner: we named it as the system's official server after reading its registry record, or it is published under Hugging Face's own domain. See what first-party means.
Connect to Hugging Face Hub and thousands of Gradio AI Applications
Remote, Streamable HTTP:https://huggingface.co/mcp?loginIts record declares no header. A server may still ask you to sign in (OAuth) when a client connects.
Remote, Streamable HTTP:https://huggingface.co/mcpIts record declares no header. A server may still ask you to sign in (OAuth) when a client connects.
Version 0.2.33. Registry record last changed .
Not checked. OSV is asked about npm and PyPI packages that name a version; this server lists none, or its record changed after the last read.
Command line
hf is a command-line tool for Hugging Face. For an agent that runs on your machine and has a shell, a command-line tool can be the simpler choice: there is no server to connect, and no tool definitions take room in the context window. See its documentation.
Read from the vendor's repository on GitHub on , most recently changed first. Weight is the skill's SKILL.md counted with OpenAI's o200k_base tokenizer: what loading it puts in a context window. Other makers' tokenizers count differently, so it compares skills with each other and is not a bill. Where a count is missing, the file's size in bytes stands in. A skill that ships scripts carries code an agent may run: read it first.
Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastru…
Discover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use this skill before any other AWS work — deploying to SageMaker, creating resources, calling AWS APIs, or anything that touches an AWS account. Use it especially when the user…
Set up an isolated Python environment for SageMaker / AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `bo…
Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like "deploy a model", "host this LLM on AWS", "serve this embedding model", "deploy a reranker", "deploy a…
Ensure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a role ARN explicitly, when scripts are…
Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image…
Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says "deploy this LLM", "host this HuggingFace model", "serve this…
Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server.
Use 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. Triggers on: "best model for X", "what model should I use for", "top models for [task]", "which model runs on my laptop/machine/de…
Run evaluations for Hugging Face Hub models using inspect-ai and lighteval on local hardware. Use for backend selection, local GPU evals, and choosing between vLLM / Transformers / accelerate. Not for HF Jobs orchestration, model-card PRs, .eval_results publication, or community-evals automation.
Use 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.
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts…
Use to select models to run locally with llama.cpp and GGUF on CPU, Mac Metal, CUDA, or ROCm. Covers finding GGUFs, quant selection, running servers, exact GGUF file lookup, conversion, and OpenAI-compatible local serving.
Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA. Use when someone asks to create, generate, ship, or publish a Space, demo, Gradio app, or playground for a LoRA — including LoRAs for Qwen-Image, Qwen-Image-Edit, LTX-Video, Wan, FLUX, SDXL, or other diffusion base mod…
Publish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to models/datasets, claiming authorship, and generating professional markdown-based research articles.
Look 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. Use when the user shares a Hugging Face paper page URL, an arXiv URL or ID, or asks to summarize, explain, or analyze a…
Build, deploy, and maintain applications on Hugging Face Spaces — Gradio / Docker / Static SDKs, ZeroGPU and dedicated hardware, model loading, debugging, buckets, inference providers, community grants. Use whenever the user asks to create or host an app on Hugging Face, port code onto ZeroGPU, fix…
Use this skill when the user wants to build tool/scripts or achieve a task where using data from the Hugging Face API would help. This is especially useful when chaining or combining API calls or the task will be repeated/automated. This Skill creates a reusable script to fetch, enrich or process d…
Track and visualize ML training experiments with Trackio. Use when logging metrics during training (Python API), firing alerts for training diagnostics, or retrieving/analyzing logged metrics (CLI). Supports real-time dashboard visualization, alerts with webhooks, HF Space syncing, and JSON output…
Trains 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 Face Jobs cloud GPUs.…
AI demos and GPU compute with Gradio Spaces and Hugging Face Spaces ZeroGPU. Use when writing or reviewing code that uses `@spaces.GPU`, configuring `python_version` or `requirements.txt` for a ZeroGPU Space, or handling ZeroGPU-specific code constraints — pickle-based process isolation, `gr.State`…
Post-train LLMs with TRL (Transformers Reinforcement Learning) — SFT, DPO, GRPO, KTO, and reward-model training. Use when writing or debugging training code with the TRL Python API or the trl CLI.
about 1,120 tokens
none
not since
Servers by other publishers
6 servers for Hugging Face that name a public repository or a package. Anyone can publish one, and we have not read their code: check the publisher and the source before giving one a credential.
In this order: live servers before deprecated ones, first-party first, a known vulnerability last, then more downloads, then a more recent push, then by name. There is no score. Downloads are from npm and pypistats, the last push from GitHub and vulnerabilities from OSV; a server's own page has the day each was read, and "not read" means we have no figure, not that there is none. See how this directory is made.
1 more server in the registry for Hugging Face with no repository and no package named. Nothing else is known about them, so they have no page here.
io.github.myworkingmemory/curated-finds
A server is listed for Hugging Face when we have named it as the system's official server, when its registry title or the last part of its registry name names Hugging Face as whole words, or when it is published under Hugging Face's own domain. See how this directory is made.
Built from agent catalog version 2026-11-13.3 of , from the MCP Registry as read on . A listing here is not an endorsement: anyone can publish a server, and we have not read its code. Names, descriptions and addresses are the publisher's own. See how this directory is made, and tell us about a wrong entry through the contact page.