Hugging Face MCP. Find models, datasets, and artifacts in one chat window.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Hugging Face MCP Server. Connect your AI agent directly to the world's largest AI model hub. Search, inspect, and manage thousands of models, datasets, and demo apps (Spaces) without leaving your chat client.
Use tools like `list_models` and `get_model_tags` to find specific artifacts, track model file structures, or check community discussions for bug reports.
What your AI agents can do
Create discussion
Starts a new conversation thread on a specified Hugging Face repository (model, dataset, or space).
Get collection
Retrieves detailed information about a specific Hugging Face collection using its slug.
Get model
Fetches all metadata for a specific Hugging Face model using its full ID.
Search the entire model hub using list_models to find artifacts based on tags, authors, or free text.
Use get_model and get_model_tags to retrieve detailed information, including the model's primary task, framework, and license.
Run list_model_files to get a file tree (weights, configs, tokenizers) for a model without downloading any data.
List available datasets using list_datasets and then inspect their internal structure with list_dataset_files.
Review or start conversations on a specific model or dataset using list_model_discussions or create_discussion.
View details and runtime status of ML demo apps (Spaces) using get_space.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Hugging Face MCP Server: 13 Tools for ML Discovery
Use these tools to list, retrieve, and inspect every asset type—models, datasets, and Spaces—on the Hugging Face Hub.
019d8446create discussion
Starts a new conversation thread on a specified Hugging Face repository (model, dataset, or space).
019d8446get collection
Retrieves detailed information about a specific Hugging Face collection using its slug.
019d8446get model
Fetches all metadata for a specific Hugging Face model using its full ID.
019d8446get model tags
Lists all technical tags and pipeline information for a given model ID.
019d8446get space
Retrieves details and runtime status for a specific Hugging Face demo Space.
019d8446get user
Verifies the authenticated Hugging Face user by returning their name, plan, and token metadata.
019d8446list collections
Lists available Hugging Face collections, allowing filtering by author or title.
019d8446list dataset files
Returns a list of filenames and paths within a specified dataset repository directory.
019d8446list datasets
Lists datasets on the Hub, filtered by search term or author, providing download and like counts.
019d8446list model discussions
Lists the active discussion threads for a given model, including thread titles and reply counts.
019d8446list model files
Returns a list of files and their sizes within a specific model repository, ideal for inspecting weights.
019d8446list models
Lists models on the Hub, allowing filtering by search term or author, and showing pipeline task tags.
019d8446list spaces
Lists available demo Spaces on the Hub, providing details on the author, SDK, and creation date.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Hugging Face, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You're hooking up your AI agent straight to the massive Hugging Face model hub. It means you can search, check out, and manage thousands of models, datasets, and demo apps (Spaces) right from your chat window. You don't gotta leave your client to do it.
Finding Models
- You can use
list_modelsto search the entire hub for models. You can filter by search terms, authors, or specific pipeline task tags. - If you need to dig into a model,
get_modelpulls all the metadata for a specific model ID. You can also runget_model_tagsto list every technical tag and pipeline detail attached to that model. - To see what files a model actually has—like weights, configs, or tokenizers—you run
list_model_files. This shows you the full file structure and sizes without downloading any data.
Digging into Datasets
list_datasetslets you list datasets on the Hub, filtering by search terms or authors, and it shows you how many people have downloaded it and how many likes it's got.- Once you pick a dataset, you can use
list_dataset_filesto get a list of all the filenames and paths inside that dataset's repository directory. - You can also check out specific datasets using
get_collection, which pulls detailed info about a collection based on its slug.
Checking Out Spaces and Community
list_spacesshows you available ML demo apps (Spaces) on the Hub, giving you the author, the SDK they use, and when it was made. To get the specific details and runtime status of one Space, you useget_space.- If you want to know what people are saying about a model or dataset,
list_model_discussionsshows you the active discussion threads for a given model, including the titles and how many replies there are. You can start a new conversation on a model, dataset, or Space usingcreate_discussion.
User Info and Organization
- You can verify the logged-in Hugging Face user and pull their name, plan, and token metadata using
get_user. list_collectionslists available Hugging Face collections, and you can filter that list by author or title.
How Hugging Face MCP Works
- 1 Subscribe to the Hugging Face server and provide your Hugging Face Access Token.
- 2 Select your AI client (e.g., Claude, Cursor, or your own agent) and initiate a query.
- 3 The agent calls the appropriate tool (e.g.,
list_modelsorlist_dataset_files) and returns the structured data directly to your chat window.
The bottom line is, your AI client handles the API calls and presents the ML hub data right where you are working.
Who Is Hugging Face MCP For?
ML Engineers, AI Researchers, and Data Developers. This is for anyone who spends time figuring out which model or dataset to use. Stop jumping between the terminal, the browser, and the documentation. This tool puts the entire ML model hub inside your agent's context.
Uses get_model_tags and list_model_files to quickly verify a model's framework, task type, and required artifacts before writing integration code.
Uses list_datasets and list_collections to discover relevant data sources and explore model relationships without leaving their research environment.
Uses get_space and list_spaces to check the live status of demo applications and find suitable model endpoints for a new application build.
What Changes When You Connect
- Find models by criteria, not by memory. Instead of manually checking tags, use
list_modelsto filter thousands of models by task type or framework. You get a structured list instantly. - Stop guessing the model structure. When you run
list_model_files, you see the exact contents of the repo—theconfig.json, the weights, the tokenizer—without having to download a single byte. - Keep your research contained. Use
list_datasetsandlist_collectionsto browse data sources and related models. You stay in your chat client and don't have to switch tabs to read dataset metadata. - Understand community consensus. Review bug reports and usage tips by calling
list_model_discussions. You get a count of active threads and the top topics, helping you decide if a model is stable. - Quickly check live demos. Use
get_spaceorlist_spacesto see if an ML demo app is currently running. This saves time debugging deployment issues before you even start coding. - Verify your assets before committing. Run
get_userto confirm your token is active and linked to the correct account details.
Real-World Use Cases
The Model Vet: Checking Artifact Readiness
An ML Engineer needs to know if a specific model, google/gemma-2-9b, is ready for production. They ask the agent to run list_model_files first. The agent returns the file tree, confirming the presence of config.json and the correct weight format. Next, they run get_model_tags to verify the required framework (e.g., PyTorch). Done. The model is verified without any manual downloads or browsing.
The Data Explorer: Finding Related Data
A Researcher needs data for a new NLP project. They first use list_datasets to find potential candidates. When they narrow it down to 'MedicalReports', they use list_dataset_files to confirm the data is in parquet format, saving them hours of manual inspection.
The Debugger: Assessing Model Stability
A Developer is considering a new model, but isn't sure if it's stable. They ask the agent to run list_model_discussions for the model. The agent shows 23 active discussions, allowing the developer to immediately see top threads about 'quantization' and 'memory requirements' before committing to the integration.
The Project Manager: Scouting Demo Apps
A PM wants to show stakeholders the best ML demo apps. They use list_spaces to get a list of available demos, checking the SDK (Streamlit vs. Gradio) and the creation date. They then use get_space to check the live runtime status of the top candidate.
The Tradeoffs
Browser Hopscotch
Opening the Hugging Face website, searching for a model, clicking into the model card, scrolling down to tags, then opening a separate tab to view discussions, and finally downloading the file structure manually.
→
Let your AI agent handle it. Ask the agent to get_model and list_model_tags in one go. Then, if you need community feedback, run list_model_discussions. All data stays in the chat.
Manual File Guesswork
Assuming a model has weights named model.safetensors when, in fact, the required files are nested in a subdirectory or use a different naming convention.
→
Run list_model_files on the repository ID. This gives you the complete, accurate file path and size, removing all guesswork.
Ignoring Dependencies
Trying to build an application using a dataset without first checking its structure, leading to data loading errors because the files are in a subdirectory like /train/.
→
Use list_dataset_files with an optional subdirectory path to map out the dataset's structure before your code ever runs.
When It Fits, When It Doesn't
Use this if you need to perform multi-step research or deep metadata inspection. You're not just looking for a model; you're building a case for one. For example, if you need to find a model, check its tags, list its files, and see its community feedback, this is the right tool. Don't use this if you just need a simple search result (e.g., 'list all models'). Instead, use a simple search query in your agent, which will trigger the necessary listing tools. This server is for deep dives, not quick lookups.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Hugging Face. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 13 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Manually checking model tags and file structures is a total time sink.
Right now, if you want to check a model's framework or see exactly what files it contains, you have to open the Hugging Face website. You click the model card, then you scroll down to the tags section. If you want the file structure, you have to navigate to the files tab. It's three different clicks and three different pages just to answer: 'Is this model PyTorch or TensorFlow?'
With the Hugging Face MCP Server, you ask your agent. It runs the `get_model_tags` tool, and boom. The tags and pipeline info appear right here. You run `list_model_files`, and the file tree shows up, all in one conversation. No switching tabs, no context loss.
Hugging Face MCP Server: Inspect model metadata on demand.
You used to have to open the Hub, find the model, and manually copy the IDs and tags into your local notes or IDE. If you missed a file, you had to manually check the file structure tab. It was slow, error-prone, and required constant context switching.
Now, your AI client handles it. You run `get_model` to pull the full metadata, then `list_model_files` to map the repo structure. You've pulled all the necessary data points for integration planning without leaving your workflow.
Common Questions About Hugging Face MCP
How do I use the `list_models` tool to find a specific type of model? +
You can filter the results by providing a search term or author name in the tool call. This narrows the thousands of available models down to relevant results, making discovery fast.
Does `get_model_tags` give me the framework and task type? +
Yes. It returns a detailed breakdown, including the model's primary task tag (like 'text-generation') and the framework it uses (like 'pytorch' or 'tensorflow').
What is the difference between `list_model_files` and `list_dataset_files`? +
list_model_files shows the artifacts inside a model repo (weights, configs). list_dataset_files shows the files inside a dataset repo (data splits, READMEs). Both map out the structure.
Can I check discussions on a model using `list_model_discussions`? +
Yes. This tool lists active threads, giving you the title, author, and comment count. This helps you gauge community interest and spot common bugs.
How do I check the status of a demo app using `get_space`? +
You provide the Space ID. The tool returns details and the current runtime status, letting you know if the demo app is live and working.
How do I find datasets using the `list_datasets` tool? +
The list_datasets tool returns dataset IDs, authors, and descriptions. You can filter results by search term or author to narrow down your search.
What information does `get_user` provide about my Hugging Face account? +
It returns metadata about your user account, including your plan, organization memberships, and access token type. This confirms your credentials are set up correctly.
How can I view the file structure of a model using `list_model_files`? +
The tool lists filenames, file sizes, and paths for a given model. You can also optionally specify a subdirectory to inspect specific folders within the model repo.
How do I get a Hugging Face Access Token? +
Log in to Hugging Face, go to Settings > Access Tokens, click New token, give it a name and select scopes (read is sufficient for browsing, write if you need to create repos). Copy the token immediately — it starts with hf_.
Can I search models by task type (e.g. text-generation)? +
Yes! Use list_models with a search query. While the search endpoint doesn't directly filter by pipeline_tag, you can search by task name (e.g. search='text-generation') and then use get_model or get_model_tags to verify the pipeline_tag of specific models.
Can I see what files are in a model repository? +
Yes! Use list_model_files with the model ID (e.g. 'google-bert/bert-base-uncased') to see the complete file tree including model weights (.safetensors, .bin), config files, tokenizer files and README. Optionally set a path to browse a specific subdirectory like 'onnx' or 'pytorch'.
Can I create discussions on model pages? +
Yes! Use create_discussion with the repo type ('model', 'dataset' or 'space'), the repo ID and a title. This creates a new discussion thread on the repository. You can use list_model_discussions first to check existing threads before creating a new one.
Multi-server workflows that include Hugging Face MCP
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
BrowserStack
Automate testing via BrowserStack — manage projects, track test builds, fetch session logs, and monitor execution pipelines from any AI agent.
Pinecone
Equip your AI agent to manage your Pinecone vector databases. Query embeddings, fetch metrics, manage collections, and run stats natively via chat.
Upstash
Manage serverless Redis via Upstash REST API — execute commands, manage data structures and monitor your database from any AI agent.
You might also like
Woodpecker CI
Manage your Woodpecker CI instance — control pipelines, monitor agents, and configure repositories directly from your AI agent.
Brasil.io
Access structured Brazilian public data — query COVID-19 stats, company records, and socio-economic datasets directly from your AI agent.
Heroku (PaaS)
Manage Heroku apps via AI — list apps, restart dynos, toggle maintenance mode, and audit config vars.