Integration

Hugging Face integration

Machine learning platform API for accessing models, datasets, and inference endpoints. Deploy and run models from the Hugging Face Hub, manage model repositories, and access the Inference Providers API for thousands of pre-trained models across NLP, vision, and audio tasks via the unified router (router.huggingface.co) and the Hub API (huggingface.co/api).

Connect Hugging Face How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Hugging Face.Built from the 20 Hugging Face tools below, on the connection you add once.

Common Hugging Face use cases

Publish models
Model discovery
Dataset discovery
Remove old models
Model documentation
Publish trained models
Build conversational chatbots
Build semantic search engines
Build multilingual applications
Build creative writing assistants

What you can do with Hugging Face

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Classification, 4 operations

image_classificationImage classificationPOSTCategorizes images into predefined classes using computer vision models.
text_classificationText classificationPOSTCategorizes text into predefined classes using trained classification models.
token_classificationToken classificationPOSTLabels individual tokens in text for Named Entity Recognition (NER) and Part-of-Speech tagging.
zero_shot_classificationZero shot classificationPOSTClassifies text into arbitrary categories without requiring model training or fine-tuning.

Model, 2 operations

get_model_infoGet model infoGETRetrieves detailed metadata for a specific model.
list_modelsList modelsGETLists available models from the Hugging Face Hub with filtering and search.

Repo, 2 operations

create_repoCreate repoPOSTCreates a new repository for models, datasets, or Spaces.
delete_repoDelete repoDELETEPermanently deletes a repository from Hugging Face Hub.

Text, 2 operations

fill_maskFill maskPOSTPredicts masked words in sentences using masked language models like BERT and RoBERTa.
text_generationText generationPOSTGenerates text continuations using various language models from the Hugging Face model hub.

Answer, 1 operation

question_answeringQuestion answeringPOSTExtracts precise answers to questions from provided context passages using extractive QA models.

Chat, 1 operation

chat_completionChat completionPOSTOpenAI-compatible chat completions endpoint supporting conversational LLMs and VLMs.

Commit, 1 operation

commit_filesCommit filesPOSTCreates a commit on a Hugging Face repository that can add, modify, or delete files.

Dataset, 1 operation

list_datasetsList datasetsGETLists available datasets from the Hugging Face Hub.

Embedding, 1 operation

feature_extractionFeature extractionPOSTGenerates dense vector representations of text for semantic similarity and machine learning tasks.

Image, 1 operation

text_to_imageText to imagePOSTCreates images from text descriptions using diffusion models like Stable Diffusion and FLUX.

Similarity, 1 operation

sentence_similaritySentence similarityPOSTComputes semantic similarity scores between a source sentence and multiple candidate sentences.

Summary, 1 operation

summarizationSummarizationPOSTCondenses long texts into concise summaries while preserving key information and meaning.

Transcription, 1 operation

automatic_speech_recognitionAutomatic speech recognitionPOSTConverts speech audio into text transcriptions using automatic speech recognition models.

Translation, 1 operation

translationTranslationPOSTTranslates text between languages using neural machine translation models.

Use Hugging Face from Claude Code, Cursor or Codex

Connect Hugging Face in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Hugging Face operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Hugging Face

Create your workspace
Sign up free. Nothing to install.
Connect Hugging Face once
Add your Hugging Face connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Hugging Face integration FAQ

What can you do with the Hugging Face integration?

LiveContext exposes 20 operations on Hugging Face, covering classification, model, repo and text. Common uses include Publish models, Model discovery and Dataset discovery.