Hugging Face MCP Server

@nikolausm

代码仓库

基本信息

分类

AI 与智能体

传输方式

stdio

作者

nikolausm

关于 Hugging Face MCP Server

MCP server for Hugging Face API integration - Access Stable Diffusion and other AI models

#huggingface #mcp-server #ai-image-generation

Hugging Face MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "huggingface": {
      "command": "node",
      "args": [
        "/path/to/huggingface-mcp-server/index.js"
      ],
      "env": {
        "HUGGINGFACE_TOKEN": ""
      }
    }
  }
}

Hugging Face MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is Hugging Face MCP Server?

An MCP (Model Context Protocol) server that provides access to Hugging Face's AI image generation models, including Stable Diffusion. It allows users to generate images from text prompts using multiple models, check API status, and manage tokens—all through the MCP interface.

How to use Hugging Face MCP Server?

Clone the repository and install dependencies with npm install. Obtain a free Hugging Face API token from your settings page and set it as the HUGGINGFACE_TOKEN environment variable. Then add the server to your Claude Desktop configuration (or any MCP client) pointing to the server's index.js file. Use the provided tools: generate_image, list_models, and check_status.

Key features of Hugging Face MCP Server

Generate images using multiple Stable Diffusion models
Support for negative prompts and guidance scale
Save images locally or return as base64
Check API status and token validity
Free tier available with rate limits
Model selection from SD2.1 to SDXL and more

Use cases of Hugging Face MCP Server

Creating children's book illustrations with specific art styles
Generating educational diagrams (e.g., anatomy posters)
Rapid prototyping of fantasy or anime-style artwork
Producing high-quality general-purpose images for content creation

常见问题

What models are available?

Stable Diffusion 2.1, Stable Diffusion XL, OpenJourney, Dreamlike Diffusion, and Anything v5 (anime/manga style).

Is there a free tier?

Yes, the free tier is rate-limited to approximately 10–20 requests per minute. Some models may experience queue times. For production use, upgrading to a paid plan is recommended.

How do I get a Hugging Face API token?

Go to https://huggingface.co/settings/tokens, create a new token (free), and copy it. Set it as the `HUGGINGFACE_TOKEN` environment variable.

How do I configure this server in Claude Desktop?

Add a `mcpServers` entry to `~/Library/Application Support/Claude/claude_desktop_config.json` with `command: "node"`, `args: ["/path/to/index.js"]`, and `env: { HUGGINGFACE_TOKEN: "your_token" }`.

What parameters can I use for image generation?

`prompt` (required), `model` (defaults to sd-2.1), `negative_prompt`, `guidance_scale` (higher values follow prompt more closely), and `save_path` (to save locally instead of base64).

AI 与智能体分类下的更多 MCP 服务器

xhostd

Agent-first hosting. From Claude, Cursor, or Codex, your agent can create an app, push code, and deploy it to a live HTTPS URL, with managed Postgres, custom domains, environment variables, backups, and rollback.

Hypnothera

La-Salida

Agent skill: turn what your AI assistant knows about you into a personalized hypnosis session on hypnothera.ai

HeyLead: LinkedIn Outreach & Lead Generation MCP Server

D4umak

HeyLead: AI agent for LinkedIn outreach. Finds the right people, writes in your voice, follows up and handles replies, from Claude Code, Cursor, any MCP client or a web dashboard.

AON — Agent Offer Network

AON

AON MCP connects AI agents to real, buyable products and services with live pricing and tracked links—enabling builders to earn developer revenue share from attributed clicks and conversions.

OpenZiti / LLM-Gateway

openziti

NetFoundry LLM Gateway is an OpenAI-compatible API proxy that routes requests across multiple LLM providers using zero-trust networking. Zero trust LLM gateway. OpenAI-compatible proxy with semantic routing and load bala