How to Use the Hugging Face MCP in Claude Code

Q: How do I use Claude Code to check Hugging Face model tags in a CI script?

In your script, call Claude Code with the getmodeltags tool and the model ID. You can then pipe the JSON output to a tool like jq to assert that a specific tag, like a license, is present.

Q: Can I script Claude Code to find new Hugging Face datasets?

Yes. You can run claude mcp tool hugging-face-mcp listdatasets --search 'yourterm' in a shell script. The output is JSON, so it's easy to parse and integrate with other command-line tools.

Q: What's the command to have Claude Code list models in a Hugging Face collection?

Use the getcollection tool with the collection's slug. For example: claude mcp tool hugging-face-mcp getcollection --slug 'my-org/my-collection'. This will return all the items in that collection.

Q: Is it possible to pipe data to Claude Code to create a Hugging Face discussion?

Yes, you can construct the arguments for the creatediscussion tool from a file or another command's output. It's designed to work seamlessly within shell pipelines for headless automation.

Automate your Hugging Face workflows from the command line. A perfect fit for your CI/CD pipelines and shell scripts with Claude Code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Hugging Face MCP to Claude Code

Create your Vinkius account to connect Hugging Face to Claude Code and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Hugging Face with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Models in Your CI/CD Pipeline

Stop letting upstream model changes break your builds. Add a step in your GitHub Actions workflow that uses Claude Code to validate a model before your deployment script runs. It's a simple check that saves a lot of headaches. A quick call to `list_model_files` can confirm that a `model.safetensors` file exists, or `get_model_tags` can verify the license hasn't changed. If the check fails, the pipeline stops, and you get notified. No surprises.

Script All Your Hub Monitoring

Get updates from the Hugging Face Hub without ever opening a browser. You can write a simple shell script and run it as a cron job. For example, have Claude Code check for new models from a specific author every morning. The script can call `list_models`, pipe the JSON output to `jq` for filtering, and then send a formatted summary to a Slack webhook. You can even use `get_user` in a health check script to confirm your API token is still valid.

Manage Repos from a Remote Server

This MCP Server is built for the terminal. If you're debugging a model on a remote machine over SSH, there's no need to switch back to your local machine to post a question on the Hub. You can do it right from the command line. Just use Claude Code with the `create_discussion` tool, passing the repo ID and your message as arguments. It's faster and keeps you in the zone. This turns the Hugging Face Hub into another command-line utility you can integrate anywhere.

Setup guide

Set up Hugging Face MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see hugging-face-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest Hugging Face transactions." It will automatically discover and invoke the available Hugging Face tools.

Terminal

claude mcp add --transport http hugging-face-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Hugging Face MCP

Paste the JSON snippet shown on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "hugging-face-mcp": {
      "type": "url",
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

Get your connection token →

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.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Hugging Face now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Hugging Face MCP in Claude Code

In your script, call Claude Code with the `get_model_tags` tool and the model ID. You can then pipe the JSON output to a tool like `jq` to assert that a specific tag, like a license, is present.

Yes. You can run `claude mcp tool hugging-face-mcp list_datasets --search 'your_term'` in a shell script. The output is JSON, so it's easy to parse and integrate with other command-line tools.

Use the `get_collection` tool with the collection's slug. For example: `claude mcp tool hugging-face-mcp get_collection --slug 'my-org/my-collection'`. This will return all the items in that collection.

Yes, you can construct the arguments for the `create_discussion` tool from a file or another command's output. It's designed to work seamlessly within shell pipelines for headless automation.

The server only touches the data required by the tool you call, such as repository IDs, search queries, or collection slugs. Security is handled by Vinkius; your requests are authenticated via a single token and executed in isolated sandboxes that leave no trace.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript