Integration

HuggingFace Hub API integration

Repository management API for the Hugging Face Hub. Browse, search, and manage models, datasets, and spaces. Create, delete, and move repositories. Access metadata for millions of ML artifacts.

Connect HuggingFace Hub API How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in HuggingFace Hub API.Built from the 17 HuggingFace Hub API tools below, on the connection you add once.

Common HuggingFace Hub API use cases

Build filter UI
Discover tag categories
Publish models
Model discovery
Space discovery
Dataset discovery
Remove old models
Track discussions
List model versions
Model documentation

What you can do with HuggingFace Hub API

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.

Repo, 5 operations

create_repoCreate repoPOSTCreates a new repository for models, datasets, or spaces.
delete_repoDelete repoDELETEPermanently deletes a repository from Hugging Face Hub.
get_trendingGet trendingGETRetrieves currently trending repositories on the Hub.
move_repoMove repoPOSTMoves or renames a repository on Hugging Face Hub.
update_repo_settingsUpdate repo settingsPUTUpdates repository settings such as visibility and access gating.

Dataset, 2 operations

get_dataset_infoGet dataset infoGETRetrieves detailed metadata for a specific dataset.
list_datasetsList datasetsGETLists available datasets from the Hugging Face Hub.

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.

Space, 2 operations

get_space_infoGet space infoGETRetrieves detailed metadata for a specific Space.
list_spacesList spacesGETLists available Spaces from the Hugging Face Hub.

Tag, 2 operations

get_dataset_tagsGet dataset tagsGETRetrieves all available dataset tags grouped by type.
get_model_tagsGet model tagsGETRetrieves all available model tags grouped by type.

Discussion, 1 operation

list_discussionsList discussionsGETLists discussions and pull requests for a repository.

File, 1 operation

list_repo_filesList repo filesGETLists files and folders in a repository tree.

Ref, 1 operation

list_repo_refsList repo refsGETLists branches, tags, and optionally pull requests for a repository.

User, 1 operation

whoamiWhoamiGETReturns the authenticated user's account information.

Use HuggingFace Hub API from Claude Code, Cursor or Codex

Connect HuggingFace Hub API in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its HuggingFace Hub API 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 HuggingFace Hub API

Create your workspace
Sign up free. Nothing to install.
Connect HuggingFace Hub API once
Add your HuggingFace Hub API 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.

HuggingFace Hub API integration FAQ

What can you do with the HuggingFace Hub API integration?

LiveContext exposes 17 operations on HuggingFace Hub API, covering repo, dataset, model and space. Common uses include Build filter UI, Discover tag categories and Publish models.