HuggingFace
OfficialConnects to Hugging Face's ecosystem to search and interact with machine learning models, datasets, and Spaces directly from your AI assistant.
This HF MCP Server provides access to Hugging Face's ecosystem of models, datasets, and Spaces, allowing AI assistants to search, analyze, and interact with ML resources directly.
What it does
- Search Hugging Face models by task or keyword
- Browse and analyze ML datasets
- Access Hugging Face Spaces and demos
- View model cards and documentation
- Explore model performance metrics
- Download model and dataset information
Best for
About HuggingFace
HuggingFace is an official MCP server published by huggingface that provides AI assistants with tools and capabilities via the Model Context Protocol. Access HuggingFace models, datasets, and Spaces easily. Utilize Hugging Face AI learning tools and transformers for adva
How to install
You can install HuggingFace in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server supports remote connections over HTTP, so no local installation is required.
License
HuggingFace is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Related Skills
Browse all skillsInstall, manage, and run ComfyUI instances. Use when setting up ComfyUI, launching servers, installing/updating/debugging custom nodes, downloading models from CivitAI/HuggingFace, managing workspaces, running API workflows, or troubleshooting node conflicts with bisect.
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.
Guide for adding a new model to the Archon engine. Use when user wants to add support for a new HuggingFace model architecture in ArchonEngine.
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.