hf-mcp-server

hf-mcp-server

MCP.Pizza Chef: huggingface

Hugging Face is the largest public library of open AI models and datasets, alongside thousands of small hosted apps that do one job each. This official connector puts that library inside your conversation: look something up, read its details, browse datasets and papers, and run the hosted apps you have chosen to switch on. In Claude it installs from the connector gallery in one click, and you sign in with a free Hugging Face account rather than hunting for a key.

Coding
Images/Design
Web/Research

Use This MCP server To

Find an open model that fits what I am building Look up a dataset without leaving the conversation Read what a recently published AI paper is about Run a hosted demo app from inside my chat Compare a few models before I commit to one

README

Hugging Face Official MCP Server

Welcome to the official Hugging Face MCP Server 🤗. Connect your LLM to the Hugging Face Hub and thousands of Gradio AI Applications.

Installing the MCP Server

Follow the instructions below to get started:

Install in Claude Desktop or claude.ai

Click here to add the Hugging Face connector to your account.

Alternatively, navigate to https://claude.ai/settings/connectors, and add "Hugging Face" from the gallery.

Install in Claude Code

Enter the command below to install in Claude Code:

claude mcp add hf-mcp-server -t http https://huggingface.co/mcp?login

Then start claude and follow the instructions to complete authentication.

claude mcp add hf-mcp-server \
  -t http https://huggingface.co/mcp \
  -H "Authorization: Bearer <YOUR_HF_TOKEN>"
Install in Gemini CLI

Enter the command below to install in Gemini CLI:

gemini mcp add -t http huggingface https://huggingface.co/mcp?login

Then start gemini and follow the instructions to complete authentication.

Install in VSCode

Click here to add the Hugging Face connector directly to VSCode. Alternatively, install from the gallery at https://code.visualstudio.com/mcp:

If you prefer to configure manually or use an auth token, add the snippet below to your mcp.json configuration:

"huggingface": {
    "url": "https://huggingface.co/mcp",
    "headers": {
        "Authorization": "Bearer <YOUR_HF_TOKEN>"
    }
Install in Cursor

Click here to install the Hugging Face MCP Server directly in Cursor.

If you prefer to use configure manually or specify an Authorization Token, use the snippet below:

"huggingface": {
    "url": "https://huggingface.co/mcp",
    "headers": {
        "Authorization": "Bearer <YOUR_HF_TOKEN>"
    }

Once installed, navigate to https://huggingface.co/settings/mcp to configure your Tools and Spaces.

hf-mcp-server FAQ

Which apps does this work in?
claude.ai and Claude Desktop from the connector gallery, plus Claude Code, Cursor, VS Code, and Gemini CLI with one line of setup.
Do I need an account?
A free Hugging Face account, yes. Most apps sign you in through a browser prompt, so there is no key to copy.
Can I use this to find a model for a specific job?
Yes — describe the job in plain words and it will search the hub and bring back matching models with their details.
How hard is the setup?
About as easy as it gets. In Claude it is a single click from the connectors gallery; other apps take one pasted line.
Can I choose which tools it exposes?
Yes. Your Hugging Face settings page controls which tools and hosted apps are switched on for your account.
Is it made by Hugging Face themselves?
Yes, this is the official server from Hugging Face, and it can also be run on your own machine if you prefer.