hf-mcp

Search Hugging Face Hub for models, datasets, and Spaces.

Updated Mar 5, 2026
One-click install
npx skills add https://github.com/Himanshu040604/codex-skills-setup --skill hf-mcp-himanshu040604
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: hf-mcp
Source: https://github.com/Himanshu040604/codex-skills-setup/tree/main/assets/codex/skills/claude-import/skills/plugins/huggingface-skills%40claude-plugins-official/hf-mcp/skills/hf-mcp
Command: npx skills add https://github.com/Himanshu040604/codex-skills-setup --skill hf-mcp-himanshu040604

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill allows AI assistants to interact with the Hugging Face Hub, enabling them to search for models, datasets, and Spaces, retrieve repository details, run code on cloud GPUs, and utilize Gradio Spaces as AI tools.

Core Features & Use Cases

  • Model & Dataset Search: Find the best models or datasets for specific tasks.
  • Repository Information: Get detailed information, including READMEs, for models and datasets.
  • Cloud Compute: Run Python scripts or training jobs on Hugging Face's GPU infrastructure.
  • Gradio Spaces Integration: Use hosted AI applications (Spaces) as tools for tasks like image generation or transcription.
  • Documentation Lookup: Search and fetch documentation for Hugging Face libraries.

Quick Start

Use the hf-mcp skill to find the best model for code generation.

Frequently Asked Questions about hf-mcp

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I search for Hugging Face models and datasets from an AI assistant?

To search for Hugging Face models and datasets, the AI assistant uses this Skill to interface with the Hub for programmatic discovery. It retrieves repository details and READMEs, requiring a connection to the Hugging Face MCP server for full search functionality.

Can I run Python scripts on cloud GPUs using Hugging Face infrastructure?

Yes, you can run Python scripts on cloud GPUs using Hugging Face infrastructure. The Skill supports executing code and training jobs via hf_jobs, enabling AI assistants to leverage Hugging Face's GPU infrastructure for cloud compute tasks.

How do I use Gradio Spaces as AI tools for tasks like image generation?

You can use Gradio Spaces as AI tools by dynamically invoking hosted applications through this Skill. It allows AI assistants to utilize Hugging Face Spaces for executing specific tasks such as image generation or transcription directly.

Do I need a Hugging Face MCP server connection to fetch model documentation?

Yes, a connection to the Hugging Face MCP server is required to fetch model documentation. This Skill enables AI assistants to search and fetch documentation for Hugging Face libraries, but full functionality depends on that server connection.

What is the best way to retrieve repository details and READMEs from the Hugging Face Hub?

The best way to retrieve repository details and READMEs from the Hugging Face Hub is by interfacing through this Skill. It enables programmatic retrieval of detailed model and dataset information directly within an AI assistant environment.