Hugging Face MCP Server
@nikolausm
About Hugging Face MCP Server
MCP server for Hugging Face API integration - Access Stable Diffusion and other AI models
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"huggingface": {
"command": "node",
"args": [
"/path/to/huggingface-mcp-server/index.js"
],
"env": {
"HUGGINGFACE_TOKEN": ""
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
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
FAQ from Hugging Face MCP Server
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).
Frequently asked questions
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).
Basic information
More AI & Agents MCP servers
MCP Client for Ollama (ollmcp)
joniglHarness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre
MCP-NixOS - Because Your AI Assistant Shouldn't Hallucinate About Packages
utensilsMCP-NixOS - Model Context Protocol Server for NixOS resources
1Panel
1Panel-dev🔥 1Panel is a modern, open-source VPS control panel — and the only one with native AI agent support. Run Ollama models, deploy OpenClaw agents, and manage your entire server stack from one clean web interface.
MCP Server - Remote MacOs Use
baryhuangThe only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App
Open Multi-Agent Canvas
CopilotKitThe open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation and add MCP servers for deep research
Comments