HuggingFace MCP Server

Widget generated by MCP Showcase
1. About
2. Examples
3. Connect & use

Introduction

The Hugging Face MCP Server connects AI assistants to Hugging Face's vast ecosystem of machine learning resources, including models, datasets, spaces (AI applications), research papers, and documentation. As an open-source offering from Hugging Face, this server provides a secure, standardized bridge between conversational AI clients and the Hub's rich collection of state-of-the-art AI tools and content.

The server exposes tools for authenticated identity checks, powerful repository search, detailed repository inspection, and a flexible filesystem-style navigation interface. Together, these tools let assistants discover trending models, preview datasets, explore AI spaces, and read research papers—all through simple, structured queries.

Whether you're browsing the latest text-generation models, inspecting a dataset's schema before use, or reading through a paper's content, the Hugging Face MCP Server makes the entire Hub programmatically accessible to your AI workflows.

Use Cases

1. Discovering Trending and Relevant Models Search across models, datasets, and spaces with filtering by author, tags, popularity, and recency to find exactly what you need.

  • Sample prompt: Find me the top 10 most downloaded text-generation models from Meta on Hugging Face, and include links to each repository.

2. Exploring and Previewing Datasets Inspect dataset structure to discover configs, splits, and schema, then preview actual rows before committing to a download or fine-tuning task.

  • Sample prompt: Show me the structure of the 'squad' dataset, then preview the first 5 rows of the training split.

3. Getting Detailed Model Information Retrieve overviews for one or more repositories to compare capabilities, licenses, and specifications side by side.

  • Sample prompt: Give me the details and overview for openai/gpt-oss-120b and meta-llama/Llama-3-70B so I can compare them.

4. Finding AI Applications (Spaces) Use semantic search and tag filtering to locate ready-to-use AI apps and demos, including MCP-server spaces.

  • Sample prompt: Search Hugging Face Spaces for text-to-image generation apps and show me the most trending ones.

5. Reading Research Papers Navigate to papers by arXiv ID to discover related resources and read the full paper content or metadata directly.

  • Sample prompt: Pull up the paper with arXiv ID 1706.03762 and summarize its key contributions for me.

6. Browsing Trending Content List trending models, datasets, spaces, or papers to stay current with the latest developments in the AI community.

  • Sample prompt: What are the top trending datasets on Hugging Face right now?

7. Navigating Repository Files Use filesystem-style commands (ls, cat, stat, find) over hf:// URIs to explore repository contents, read config files, or locate specific files.

  • Sample prompt: List all the files in the mistralai/Mistral-7B-v0.1 model repository and show me the contents of its config.json.

8. Searching Documentation Query Hugging Face's product documentation to find guidance on transformers, datasets, or other libraries.

  • Sample prompt: Search the Hugging Face Transformers documentation for how to use the Trainer API.

9. Author-Scoped Discovery Filter searches to a specific organization or user to survey their entire catalog of contributions.

  • Sample prompt: Show me all the datasets published by the 'google' organization on Hugging Face, sorted by likes.

10. Verifying Authentication Context Confirm the identity of the authenticated user driving Hub interactions.

  • Sample prompt: Which Hugging Face account am I currently authenticated as?

Details

MCP Server URL:
https://huggingface.co/mcp?login
Type:
HTTP Stream
Authentication:
API Key (Bearer Token)
How to connect this MCP server

Tools

hf_whoami
Hugging Face tools are being used by authenticated user 'anwendo'
hub_repo_search
Search Hugging Face repositories with a shared query interface. You can target models, datasets, spaces, or aggregate across multiple repo types in one call. Include links to repositories in your response.
hub_repo_details
Get details for one or more Hugging Face repos (model, dataset, or space). Auto-detects type unless specified. For datasets, use operations: overview, dataset_structure, dataset_preview. Use dataset_structure first to discover configs, splits, sizes, and schema. Use dataset_preview only when config and split are known, unless the dataset has a single config/split.
hf_fs
Use to access the Hugging Face Hub. Navigate resources with ls, cat, find, stat, and search over hf:// URIs. Roots: hf://models, hf://datasets, hf://spaces, hf://buckets, hf://collections, hf://papers, hf://docs. For papers, ls hf://papers/ARXIV_ID to discover related resources; cat hf://papers/ARXIV_ID/paper.md or metadata.json. Documentation paths include the current version from each product's llms.txt manifest. Grammar; each token below is one args array element: ls URI [(-R|-r|-lR|-laR|--recursive)] [(-l|-a|-la|-al|--long)] [--glob GLOB] [(-type|--type|--entry-type) TYPE] [--sort SORT] [(-limit|--limit) N] cat URI [RELATIVE_PATH] [(-offset|--offset) N] [(-max-bytes|--max-bytes) N] stat URI [RELATIVE_PATH] find URI [(-R|-r|--recursive)] [(-name|--name|--glob) GLOB] [(-path|--path) GLOB] [(-type|--type|--entry-type) TYPE] [(-limit|--limit) N] search URI [QUERY...] [(-type|--type|--entry-type) TYPE] [--sort SORT] [--tag TAG] [--kind mcp] [(-limit|--limit) N] TYPE = file|dir|repo|bucket|collection|paper|link. Type aliases: f=file, d=dir, l=link, model|dataset|space=repo. SORT = createdAt|downloads|likes|lastModified|likes30d|trendingScore|mainSize|id|trending|upvotes. URI starts with hf://. QUERY and GLOB are each one string token. Search URI: hf://models|datasets|spaces[/OWNER], hf://collections[/OWNER], any hf://docs scope, or exactly hf://papers; not hf://. Repository and collection searches may omit QUERY to browse or filter; documentation and paper searches require it. Search joins multiple positional QUERY tokens with spaces. Cat and stat join one RELATIVE_PATH token to URI. Long-list flags are accepted for compatibility; hf_fs listings are already structured, so they do not alter output. Find is already recursive, so recursive flags are accepted without altering behavior. Space search: hf://spaces uses semantic search; repeat --tag to require tags, or use --kind mcp for --tag mcp-server. hf://spaces/OWNER uses owner-scoped keyword search. Documentation: ls hf://docs for products; search any docs scope; use returned hf:// URIs verbatim. Trending listings: ls hf://models/trending, hf://datasets/trending, or hf://spaces/trending. They return up to 20 entries. Trending paths imply trending order; --sort trending|trendingScore is redundant but valid. Trending papers: ls hf://papers/trending. TYPE filters mixed results; omit it when the URI already fixes the result type. Limits and path-specific behavior are documented at hf://README.md. Omit --limit and --sort unless the request asks for a cap, ordering, or exhaustive results. No pipes, redirects, shell expansion, or multiple commands.

Want to create a similar playground for your MCP?

Get Started Explore other servers