# Hugging Face Spaces

> Use this tool when you need to integrate machine learning models into your AI assistant workflows, allowing for seamless interaction with Hugging Face Spaces-hosted models. It solves problems of model accessibility and compatibility, handling parameter conversion, file uploads, and progress notifications. The tool takes in model inputs and returns outputs in various formats, including text, images, and audio files, making it ideal for workflows requiring specialized AI models within a conversation interface.

Canonical page: https://skillsregistry.net/skills/hugging-face-spaces  
JSON: https://api.skillsregistry.net/v1/skills/hugging-face-spaces

## Description

MCP-HFSpace provides a bridge between Claude Desktop and Hugging Face Spaces, allowing AI assistants to interact with machine learning models hosted on Hugging Face. Built by Shaun Smith, this Node.js implementation automatically discovers and exposes Gradio endpoints as MCP tools, handling parameter conversion, file uploads, and progress notifications. It supports various output types including text, images, and audio files, with special handling for Claude Desktop compatibility. The server runs locally using stdio transport, making it ideal for workflows requiring access to specialized AI models without leaving the conversation interface.

## Trust

- **Trust score (0–1):** 0.79
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/hugging-face-spaces)
- **Repository:** <https://github.com/xiyuefox/mcp-hfspace>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "hugging-face-spaces"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/hugging-face-spaces` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/hugging-face-spaces/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt