npx skills add ...
npx skills add huggingface/skills --skill hf-mcp
npx skills add huggingface/skills --skill hf-mcp
Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server.
Connect AI assistants to the Hugging Face Hub. Setup: https://huggingface.co/settings/mcp
| Goal | Tool |
|---|---|
| Find models | model_search |
| Find datasets | dataset_search |
| Find Spaces/apps | space_search |
| Find papers | paper_search |
| Get repo README/details | hub_repo_details |
| Learn library usage | hf_doc_search → hf_doc_fetch |
| Run code on GPU/CPU | hf_jobs |
| Use Gradio apps as tools | dynamic_space |
| Generate images | gr1_flux1_schnell_infer or dynamic_space |
| Check auth | hf_whoami |
sort="trendingScore" to find what's popular nowsort="downloads" to find battle-tested optionsmcp=true in space_search to find Spaces usable as toolsinclude_readme=true in hub_repo_details for full model/dataset documentationsecrets: {"HF_TOKEN": "$HF_TOKEN"}dynamic_space(operation="discover") to see all available Space-based tasksUser: "Find a tool that can remove image backgrounds"
1. space_search(query="background removal", mcp=true)
2. dynamic_space(operation="view_parameters", space_name="result-space-id")
3. dynamic_space(operation="invoke", space_name="result-space-id", parameters="{...}")User: "Create an image of a robot reading a book"
1. dynamic_space(operation="discover") # See available tasks
2. gr1_flux1_schnell_infer(prompt="a robot sitting in a library reading a book, warm lighting, detailed")User: "What are the latest papers on RLHF?"
1. paper_search(query="reinforcement learning from human feedback", results_limit=10)
2. hub_repo_details(repo_ids=["paper-linked-model"], include_readme=true) # If paper links to modelsUser: "How do I fine-tune with LoRA using PEFT?"
1. hf_doc_search(query="LoRA fine-tuning", product="peft")
2. hf_doc_fetch(doc_url="https://huggingface.co/docs/peft/...")User: "Run this Python script on a GPU"
hf_jobs(operation="uv", args={
"script": "# /// script\n# dependencies = [\"torch\"]\n# ///\nimport torch\nprint(torch.cuda.is_available())",
"flavor": "t4-small"
})User: "Run my training script on an A10G"
hf_jobs(operation="run", args={
"image": "pytorch/pytorch:2.5.1-cuda12.4-cudnn9-runtime",
"command": ["/bin/sh", "-lc", "pip install transformers trl && python train.py"],
"flavor": "a10g-small",
"secrets": {"HF_TOKEN": "$HF_TOKEN"}
})User: "What's happening with my training job?"
1. hf_jobs(operation="ps")
2. hf_jobs(operation="logs", args={"job_id": "job-xxxxx"})User: "What models are trending right now?"
model_search(sort="trendingScore", limit=20)User: "Tell me about Mistral-7B"
hub_repo_details(repo_ids=["mistralai/Mistral-7B-v0.1"], include_readme=true)User: "Find GGUF versions of Llama 3"
model_search(query="Llama 3 GGUF", sort="downloads", limit=10)User: "Transcribe this audio file"
1. space_search(query="speech to text transcription", mcp=true)
2. dynamic_space(operation="view_parameters", space_name="openai/whisper")
3. dynamic_space(operation="invoke", space_name="openai/whisper", parameters="{\"audio\": \"...\"}")User: "Run this data sync every day at midnight"
hf_jobs(operation="scheduled uv", args={
"script": "...",
"cron": "0 0 * * *",
"flavor": "cpu-basic"
})