HuggingFace MCP Server
HuggingFace MCP server provides AI assistants with access to the model hub — search 1M+ models, discover datasets, explore Spaces, read papers, and fetch documentation directly through MCP.
Overview
The HuggingFace MCP Server is the official Model Context Protocol integration for the HuggingFace Hub — the world's largest collection of machine learning models, datasets, and demos. It lets AI assistants search and discover models, explore datasets, browse Spaces, read ML papers, and fetch up-to-date documentation without leaving the conversation.
Remote MCP Server:
Hugging Face hosts a remote MCP server at huggingface.co/mcp. Append ?login (huggingface.co/mcp?login) for the login flow.
Key Features
Model Discovery
Search 1M+ models by task, framework, license, and popularity with detailed metadata
Dataset Explorer
Find and inspect datasets across NLP, vision, audio, tabular, and multimodal domains
Spaces Discovery
Explore interactive ML demos and applications deployed as HuggingFace Spaces
Research Papers
Search daily ML papers, filter by upvotes, and access paper details with citations
Documentation Search
Search and fetch HuggingFace library docs (Transformers, Diffusers, Datasets, PEFT) live
Image Generation
Generate images directly through hosted Spaces using Gradio-powered models
Available Tools
Built-in tools, exactly as named in the Hugging Face docs:
| Tool | Purpose |
|---|---|
hf_fs | Navigate the Hub efficiently, including semantic searches of documents and Spaces |
Contribute Repos | Create repositories and write files to those created repositories |
Sandboxes | Create and use Sandboxes, including Sandbox file management |
Run and Manage Jobs | Run, monitor, and schedule jobs on Hugging Face infrastructure |
Extra tools can be enabled from your MCP settings page on huggingface.co, and community Gradio Spaces can expose their functions as additional tools.
Installation
The remote MCP server is available at: https://huggingface.co/mcp
For the login flow, use https://huggingface.co/mcp?login. For token auth, send your Hugging Face token in the Authorization: Bearer header:
"huggingface": {
"url": "https://huggingface.co/mcp",
"headers": {
"Authorization": "Bearer <YOUR_HF_TOKEN>"
}
}
Claude Code:
claude mcp add hf-mcp-server -t http https://huggingface.co/mcp?login
Or with an explicit token:
claude mcp add hf-mcp-server \
-t http https://huggingface.co/mcp \
-H "Authorization: Bearer <YOUR_HF_TOKEN>"
Gemini CLI:
gemini mcp add -t http huggingface https://huggingface.co/mcp?login
Example Use Cases
- Model Selection: Ask your AI assistant to find the best open-source LLM for your use case, comparing licenses, context windows, and performance benchmarks
- Research Discovery: Find papers about a topic, such as vision-language models
- Documentation Lookup: Fetch exact Transformers or Diffusers API references without leaving your IDE
- Dataset Search: Find training datasets by task, language, and size with licensing details
- Demo Exploration: Discover interactive Spaces for a specific technology to understand capabilities before implementation
Security
Authenticate via the login flow (https://huggingface.co/mcp?login) or send a Hugging Face token in the Authorization: Bearer header. Manage which tools and Spaces your server exposes from your MCP settings page on huggingface.co.
Sources
Related Articles & Guides
#MCP ServerKnowledge Graph Memory MCP: AI Persistent Memory & Entity Mgmt
Knowledge Graph Memory MCP servers empower AI with persistent memory, entity management, and relation tracking through local knowledge graph interaction.
MiniMax MCP Server
Integrate MiniMax text-to-speech, voice, image, and video generation APIs with MCP clients.
#MCP ServerOllama Deep Researcher: AI Model for Web Search & LLM Synthesis
Ollama Deep Researcher MCP servers enable AI models to perform advanced topic research using web search and LLM synthesis, powered by a local MCP server.