AI

Hugging Face

Open-source platform for machine learning that provides access to thousands of pre-trained models, datasets, and tools for building, training, and deploying ML applications.

Hugging Face MCP, Integrations & Automations for Enterprise AI Agents

Connect your AI agents to Hugging Face MCP in minutes. No field mapping. No code required. Adopt AI's zero-shot API discovery means your agents understand Hugging Face's schema on first contact - and can act on it instantly.

Generate MCP URL

What Your AI Agents Can Do

Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Whoami on Hugging Face
Returns the authenticated user or org context from GET /whoami-v2. Use to verify tokens and read username for HF_LIST_USER_MODELS. Does not return fine-grained scopes in all cases.
Hub Papers Claim on Hugging Face
Claim paper authorship (POST /settings/papers/claim).
Hub Repo Xet Read Token on Hugging Face
Get Xet read token for rev.
Hub Jobs List on Hugging Face
List jobs in a namespace.
Summarization on Hugging Face
Summarizes long input text with seq2seq summarization models. Returns summary string and optional metadata. Use when the model is tagged summarization; for chat-style summaries HF_TEXT_GENERATION may be simpler.
Hub SQL Console Embed Create on Hugging Face
Create SQL console embed for a dataset/model repo.
Hub Collection Items Batch Slug ID on Hugging Face
Batch add items (slug-id collection).
Hub Collection Patch By Slug on Hugging Face
PATCH collection by slug only.
Hub Trending Get on Hugging Face
Hub-wide trending feed (models/spaces/datasets mix). Complements HF_LIST_TRENDING_MODELS which filters /models only.
Hub Discussion Storage Get on Hugging Face
Storage metadata for discussion.
Hub Repos Move on Hugging Face
Move or rename a repository (POST /repos/move).
Get Model on Hugging Face
Fetches a single model repository metadata JSON from the Hub. Returns siblings, pipeline_tag, and config pointers. Use before picking an Inference model id; use HF_LIST_MODELS to browse.
Hub Repo Tree on Hugging Face
List files at a revision (tree API).
Hub Gated Access Handle on Hugging Face
Approve/deny access request (admin).
Hub Collection Items Add Slug on Hugging Face
Add item to collection (slug-only form).
Delete Endpoint on Hugging Face
Deletes an Inference Endpoint permanently. Returns confirmation. Use to tear down unused spend; irreversible unlike HF_PAUSE_ENDPOINT.
Hub Space Volumes Put on Hugging Face
Configure Space persistent volumes.
Create Endpoint on Hugging Face
Creates a new Inference Endpoint (POST /v2/endpoint). Returns creation status. Use for production model hosting; body must follow HF cloud schema (repository, accelerator, etc.).
Hub Discussions List on Hugging Face
List discussions/PRs for a repo.
Hub Repo Settings Put on Hugging Face
Update repo settings JSON.
Get Endpoint on Hugging Face
Fetches configuration and health for a dedicated Inference Endpoint by namespace and name. Returns replica status and URL. Use after HF_LIST_ENDPOINTS; for public Inference API models use HF_TEXT_GENERATION without an endpoint.
Automatic Speech Recognition on Hugging Face
Transcribes speech to text (Whisper, Wav2Vec2, etc.). Returns text and optional chunks. Use for voice notes and meetings; for classification of audio use HF_AUDIO_CLASSIFICATION.
Resume Endpoint on Hugging Face
Resumes a paused Inference Endpoint and provisions replicas. Returns status transitions. Use after HF_PAUSE_ENDPOINT; for cold-start cost savings consider HF_SCALE_TO_ZERO if supported on your account.
Hub Post Delete on Hugging Face
Delete a community post.
Hub Docs Search on Hugging Face
Search Hub documentation.
Hub Repo Scan on Hugging Face
Security/scan status for model or dataset repo.
List Models on Hugging Face
Queries the Hub model index with filter, search, sort, limit, author, and tags parameters. Returns model cards metadata and download stats. Paginate with cursor/limit as returned by API. Use HF_SEARCH_MODELS for a focused text search preset.
Hub Blog Comment Reply on Hugging Face
Reply to a blog comment (global slug).
Hub Notifications Delete on Hugging Face
Clear or delete notifications (DELETE /notifications).
Hub Datasets Tags By Type Get on Hugging Face
Tag catalog for datasets grouped by type.
Hub Gated Access Grant on Hugging Face
Grant access directly (admin).
Hub Job Duplicate on Hugging Face
Duplicate job definition.
Hub Gated Access Cancel on Hugging Face
Cancel your pending access request.
Hub Org Member Role Put on Hugging Face
Update a member role in an organization.
Hub Papers List on Hugging Face
List arXiv papers on the Hub.
Hub Repo Lfs Batch on Hugging Face
Batch LFS preupload metadata.
Question Answering on Hugging Face
Answers a question given a context passage via extractive QA models. Returns answer text, score, and start/end offsets. Use when you have a fixed context string; for generative RAG over chat models use HF_TEXT_GENERATION with a prompt instead.
Hub Models Tags By Type Get on Hugging Face
Tag catalog for models grouped by type (different from HF_GET_MODEL_TAGS /models-tags).
Hub Repos Create on Hugging Face
Create a new model, dataset, or space repository (POST /repos/create).
List Spaces on Hugging Face
Lists Spaces with optional search/filter/limit. Returns Space metadata including SDK and hardware hints. Use for demos and apps; not for Inference Endpoints management.
Hub Collection Item Delete Slug ID on Hugging Face
Remove one item from collection (slug-id).
List User Models on Hugging Face
Lists models authored by a Hub username via author= filter. Returns that user’s public model repos. Use after HF_WHOAMI to pass your username; for global search use HF_SEARCH_MODELS.
List Trending Models on Hugging Face
Lists models sorted by Hub trending signal with configurable limit. Returns models gaining traction recently. Use for discovery; for raw download ranking use HF_SEARCH_MODELS with sort=downloads.
Image Classification on Hugging Face
Classifies an image input and returns top labels with scores. Send base64 data URL or raw bytes per Inference API conventions in inputs field as JSON. Use for vision checkpoints; for detection use HF_OBJECT_DETECTION.
Hub Repo Lfs Delete on Hugging Face
Delete one LFS object by sha from repo.
List Endpoints on Hugging Face
Lists your Inference Endpoints on Hugging Face (managed GPU/CPU deployments). Returns paginated endpoint records with status and URLs. Use before HF_GET_ENDPOINT; requires a token with inference endpoints scope.
Update Endpoint on Hugging Face
Updates an Inference Endpoint (PUT /v2/endpoint/ns/name). Returns updated spec. Use to change instance type or image revision; pair with HF_PAUSE_ENDPOINT when maintenance is needed.
Hub User Overview Get on Hugging Face
Public overview for a Hub username.
List Orgs For User on Hugging Face
Lists organizations the authenticated user belongs to (GET /organizations). Returns org names and roles when permitted. Use for multi-tenant Hub workflows; unrelated to model inference.
Hub Ie Namespace Auth Check on Hugging Face
Check inference-endpoint permissions for namespace.
Text2text Generation on Hugging Face
Runs encoder–decoder generation (T5, BART, FLAN) via the Inference API. Returns generated text for summarization, translation, or conditional generation tasks. Use instead of HF_TEXT_GENERATION when the model card shows text2text-generation; for causal LMs use HF_TEXT_GENERATION.
Text Classification on Hugging Face
Classifies text (sentiment, topic, etc.) and returns an array of {label, score}. Use when the model is a sequence-classification checkpoint. For free-form labels without fine-tuning use HF_ZERO_SHOT_CLASSIFICATION instead.
Object Detection on Hugging Face
Detects objects with bounding boxes, labels, and scores. Returns structured detections. Use for localization tasks; for captions use HF_IMAGE_TO_TEXT.
Hub Jobs Create on Hugging Face
Create a job (POST body).
Hub Repo Commit on Hugging Face
Create a commit (add/delete/update operations in JSON body).
Text To Image on Hugging Face
Runs diffusion models from a text prompt. Returns image bytes or base64 per API response. Parameters JSON may include negative_prompt, width, height, num_inference_steps, guidance_scale. Use for creative assets; not for text embeddings.
Pause Endpoint on Hugging Face
Pauses billing for a dedicated endpoint while preserving configuration. Returns updated status. Use overnight or in dev; resume with HF_RESUME_ENDPOINT when traffic returns.
Hub Papers Index on Hugging Face
Submit or refresh paper index (POST /papers/index).
Hub Repo Resolve Cache on Hugging Face
Resolve cached blob URL path for a file at rev.
Hub Job Cancel on Hugging Face
Cancel a running job.
Table Question Answering on Hugging Face
Answers natural language questions over a structured table (TAPAS-style). Pass inputs JSON with query and table fields. Use for spreadsheet QA; for free-text RAG use HF_QUESTION_ANSWERING or HF_TEXT_GENERATION.
Hub Repo Resource Group Get on Hugging Face
Get resource group linkage for repo.
Hub Repo Notebook on Hugging Face
Fetch notebook file JSON at rev/path.
Get Dataset on Hugging Face
Gets dataset repository metadata for a dataset id. Returns readme refs and download stats. Use when wiring training jobs; use HF_LIST_DATASETS to discover names.
Hub Gated Ask Access on Hugging Face
Request access to a gated model or dataset.
Audio Classification on Hugging Face
Classifies audio clips into categories. Pass audio as base64 or URL per model expectations in inputs JSON. Use for environmental sound or speech emotion classifiers; for transcripts use HF_AUTOMATIC_SPEECH_RECOGNITION.
Search Datasets on Hugging Face
Shortcut dataset search with sort=downloads and configurable limit (e.g. search=imdb). Returns dataset cards for benchmarking. Use HF_LIST_DATASETS when you need raw filter strings instead.
Hub Papers Search on Hugging Face
Hybrid semantic / full-text paper search.
Hub Repo Super Squash on Hugging Face
Super-squash history at rev (destructive; models/datasets/spaces per account).
Token Classification on Hugging Face
Performs NER or token tagging and returns entities with entity, score, start, end, word indices. Use for structured span extraction from text. For whole-document labels use HF_TEXT_CLASSIFICATION.
Hub Repo Treesize on Hugging Face
Directory size summary at rev/path.
Hub Jobs Count on Hugging Face
Count jobs in namespace.
Hub Settings Mcp Get on Hugging Face
MCP-related settings for the account (if enabled).
Search Models on Hugging Face
Shortcut for popular model discovery: GET /models?search=query&sort=downloads&limit=10. Returns top downloaded matches for the query string. Use for “find a Llama/Mistral checkpoint”; for full filters use HF_LIST_MODELS.
Hub Kernel Revision Get on Hugging Face
Kernel at specific git revision.
Hub Repo Xet Write Token on Hugging Face
Get Xet write token for rev.
Hub Collection Items Batch Slug on Hugging Face
Batch add items (slug-only collection).
Hub Repo Branch Create on Hugging Face
Create branch (body: startingPoint, emptyBranch, overwrite).
Hub Notifications Get on Hugging Face
List notifications for the authenticated user.
Hub Repo Lfs List on Hugging Face
List LFS files in repo.
Zero Shot Classification on Hugging Face
Classifies text into caller-provided candidate labels without task-specific heads. Returns scores per label sorted by confidence. Use for quick taxonomy mapping; for trained class heads prefer HF_TEXT_CLASSIFICATION.
Hub Gated Access List on Hugging Face
List access requests (admin); status path segment e.g. pending.
Hub Collection Items Add Slug ID on Hugging Face
Add item to collection (slug-id form).
Scale To Zero on Hugging Face
Requests scale-to-zero behavior where the platform spins down idle endpoints (account/feature dependent). Returns updated scaling policy metadata when accepted. Use to minimize cost; contrast with HF_PAUSE_ENDPOINT for explicit off.
Hub Space Events Get on Hugging Face
Space deployment events.
Hub Discussion Create on Hugging Face
Open a new discussion or PR (body JSON).

Connect Hugging Face MCP using Adopt AI in 3 Simple Steps

  1. Run a single command in your terminal to install the Hugging Face MCP server locally, no complex setup, no cloud dependency.
  2. A browser window opens automatically, where you can securely authenticate with your Hugging Face account with one click.
  3. Restart your AI client, and your agents instantly have full access to models, datasets, spaces, and every Hugging Face object, ready to read, write, and automate.

Use Cases for Hugging Face MCP

1. Model Discovery & Deployment

AI agents search the Hugging Face Hub for pre-trained models, evaluate their benchmarks, and deploy the best-fit model for your use case in minutes.


2. Automated Fine-Tuning Pipelines

AI agents orchestrate fine-tuning workflows on Hugging Face, managing datasets, training runs, and model versioning for custom NLP and vision tasks.


3. Dataset Curation & Management

AI agents browse, filter, and pull datasets from Hugging Face to build training pipelines, ensuring data quality and compatibility with target model architectures.


4. Inference API Integration

AI agents call Hugging Face Inference APIs to run predictions � text generation, classification, translation, and more � directly within enterprise workflows.


5. Model Performance Monitoring

AI agents track model metrics on Hugging Face, compare versions, detect performance drift, and trigger retraining workflows when accuracy drops below thresholds.

Explore Similar Apps  

Explore Other Apps

Frequently Asked Questions

Do I need my own developer credentials to use Hugging Face MCP with Adopt AI?

No, you can get started immediately using Adopt AI's built-in Hugging Face integration. For production use, we recommend configuring your own API tokens for greater control and security.


Can I connect Hugging Face with other apps through Adopt AI?

Yes! Adopt AI supports multi-app workflows, so your AI agents can seamlessly move data between Hugging Face and data platforms, vector databases, deployment tools, and more.


Is Adopt AI secure?

Absolutely. Adopt AI is SOC 2 Type 2 certified and ISO/IEC 27001 compliant, and adheres to EU GDPR, CCPA, and HIPAA standards. All data is encrypted in transit and at rest, ensuring the confidentiality, integrity, and availability of your data. Learn more here.


What happens if the Hugging Face API changes?

Adopt AI maintains and updates all integrations automatically, so your agents always work with the latest API versions, no manual maintenance required.


Do I need coding skills to set up the Hugging Face integration?

Not at all. Adopt AI's zero-shot API discovery means your agents understand Hugging Face's schema on first contact. Setup takes minutes with no code required.


How do I set up custom Hugging Face MCP in Adopt AI?

For a step-by-step guide on creating and configuring your own Hugging Face API tokens with Adopt AI, see here.