Skip to content
TrustedSkillsbeta
Back to all skills

hf-mcp

Official
huggingface·v1.0.0·agents·Apache-2.0

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

Install on your platform

Showing OpenClaw.

  1. 1

    Run this in your terminal

    terminal
    $

What we know about this skill

Publisher

huggingface

Matched to the vendor's own GitHub organisation.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned huggingface/skills at 80f9fa530e.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
80f9fa530e
Manifest
hf-mcp/skills/hf-mcp/SKILL.md
Scanned
1 file, 149 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

This skill allows an agent to interact with the Hugging Face Hub using its Model Compute Pipeline (MCP) server tools. It enables searching for models, datasets, Spaces, and papers hosted on the Hub. The agent can also retrieve repository details, access documentation, initiate compute jobs, and utilize Gradio Spaces as integrated AI tools.

When to use it

  • Researching new NLP models: An agent could be tasked with finding state-of-the-art sentiment analysis models available on the Hugging Face Hub.
  • Finding datasets for a specific task: The agent can locate suitable datasets, such as image classification or text summarization, hosted on the Hub.
  • Integrating interactive demos: An agent could use Gradio Spaces to provide users with an interactive interface for testing different models.
  • Automating compute tasks: The agent could be used to initiate and monitor training jobs or inference pipelines using resources available through Hugging Face's infrastructure.

Key capabilities

  • Search for models, datasets, Spaces, and papers on the Hugging Face Hub.
  • Retrieve repository details (e.g., commit history, file structure).
  • Access documentation associated with Hugging Face resources.
  • Run compute jobs on the Hugging Face Hub.
  • Utilize Gradio Spaces as AI tools.

Example prompts

  • "Find me the top 5 most downloaded text classification models on the Hugging Face Hub."
  • "What is the documentation for the 'bert-base-uncased' model?"
  • "Launch a compute job to fine-tune this model using this dataset."

Tips & gotchas

  • This skill requires an active connection to the Hugging Face Hub via MCP server tools. Without that connection, it will not function.