Hugging Face
A Model Context Protocol server that provides Claude and other LLMs with read-only access to Hugging Face Hub APIs, enabling interaction with models, datasets, spaces, papers, and collections through natural language.
What is Hugging Face?
Hugging Face is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model context protocol server that provides claude and other llms with read-only access to hugging face hub apis, enabling interaction with models, datasets, spaces, papers, and collections through na...
A Model Context Protocol server that provides Claude and other LLMs with read-only access to Hugging Face Hub APIs, enabling interaction with models, datasets, spaces, papers, and collections through natural language.
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Model Context Protocol server that provides Claude and oth
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx hugging-face-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Hugging Face
The Hugging Face MCP server gives AI assistants read-only access to the full Hugging Face Hub through the official MCP endpoint at huggingface.co/mcp, covering models, datasets, Spaces, papers, and collections. It supports both authenticated and unauthenticated access, with a Hugging Face token unlocking private repositories and higher rate limits. Data scientists and ML engineers use it to search and inspect Hub resources, discover Gradio-powered AI apps, and integrate Hub data into AI-driven research workflows.
Prerequisites
- A Hugging Face account at huggingface.co (free)
- A Hugging Face User Access Token from huggingface.co/settings/tokens (required for private repos and higher rate limits)
- An MCP-compatible client — Claude Code, Claude Desktop, VS Code, or Cursor
- No local build or npm install required — the server is hosted by Hugging Face
Create a Hugging Face access token
Go to huggingface.co/settings/tokens, click 'New token', give it a name, and select at minimum 'Read' scope. Copy the generated token.
Add the server to Claude Code via CLI
Use the Claude Code CLI to register the hosted MCP server with your token as an Authorization header.
claude mcp add hf-mcp-server -t http https://huggingface.co/mcp \
-H "Authorization: Bearer YOUR_HF_TOKEN"Configure available tools on Hugging Face
Visit huggingface.co/settings/mcp to select which Hub tools and Spaces are exposed through your MCP connection. This is a web UI provided by Hugging Face.
Verify the connection
Ask Claude to search for a model or dataset. A successful response confirms the server is connected and authenticated.
Optional: add to VS Code or Cursor config
For editor-based MCP clients, add the server as a URL-type entry with the Authorization header in your settings JSON.
Hugging Face Examples
Client configuration
VS Code or Cursor config for the Hugging Face MCP server using the hosted HTTP endpoint. Replace YOUR_HF_TOKEN with your actual token.
{
"mcpServers": {
"huggingface": {
"url": "https://huggingface.co/mcp",
"headers": {
"Authorization": "Bearer YOUR_HF_TOKEN"
}
}
}
}Prompts to try
Sample prompts to explore Hub models, datasets, Spaces, and papers.
- "Search Hugging Face for the most downloaded text-to-image models."
- "Find datasets on Hugging Face related to multilingual sentiment analysis."
- "Show me the top Spaces on Hugging Face for image generation."
- "Look up the Hugging Face paper on LLaMA 3 and summarize its key contributions."
- "List collections on Hugging Face tagged with 'diffusion models'."
- "What are the newest models fine-tuned on code generation tasks?"Troubleshooting Hugging Face
Requests return 401 Unauthorized
Verify your token is correct and has at least Read scope. Go to huggingface.co/settings/tokens, regenerate the token if needed, and update your MCP config header with the new value.
Private repositories or gated models are not accessible
Ensure your token has the appropriate scopes for the resources you need. For gated models, you must also accept the model's license on the Hugging Face website before access is granted.
The server times out or returns no results
The default HF_API_TIMEOUT is 12.5 seconds. Heavy queries may exceed this. Try narrowing your search query. Also confirm that huggingface.co is reachable from your network — some corporate networks block it.
Frequently Asked Questions about Hugging Face
What is Hugging Face?
Hugging Face is a Model Context Protocol (MCP) server that model context protocol server that provides claude and other llms with read-only access to hugging face hub apis, enabling interaction with models, datasets, spaces, papers, and collections through natural language. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Hugging Face?
Follow the installation instructions on the Hugging Face GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Hugging Face?
Hugging Face works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Hugging Face free to use?
Yes, Hugging Face is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Hugging Face Alternatives — Similar Data Science & ML Servers
Looking for alternatives to Hugging Face? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Hugging Face in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Hugging Face?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.