How to Use the Hugging Face MCP in Claude Code

Integrate Hugging Face model discovery and inference into your shell scripts and CI/CD pipelines 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

Run Hugging Face from Your Terminal

This MCP Server exposes Hugging Face Hub operations as simple commands. You can pipe data directly into inference tools. For example: `cat article.txt | claude mcp run hugging-face-alternative-mcp.run_summarization`. It's built for scripting. You can check the health of the API with `check_hf_status` in a cron job or use `list_models_by_task` in a shell script to find the latest models and trigger a new build pipeline.

Build Headless Automation Pipelines

Use this MCP Server in your CI/CD workflows. A GitHub Action could run a script that uses `list_models_by_author` to check for new model versions from your organization. If a new model is found, the script could automatically pull its metadata with `get_model`, run a benchmark using `run_inference`, and then post the results to a Slack channel. All of this runs headlessly, with no browser needed.

The Hugging Face MCP Server for CI/CD

This isn't for conversational chat; it's for getting work done. Integrate text processing into any backend service by calling `run_text_classification` or `run_text_generation` from a script. The output is clean JSON, so you can easily parse it with `jq` or another command-line tool. This lets you build powerful data processing pipelines that connect different services together, all orchestrated from your terminal.

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-alternative-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-alternative-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-alternative-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

You call the Hugging Face MCP Server directly from a shell script in your workflow file. For example, use `claude mcp run hugging-face-alternative-mcp.list_models` to fetch models and pipe the JSON output to the next step in your job.

Yes, all tools return structured JSON output by default. This makes it easy to parse results with tools like `jq` and integrate the server into your existing scripts and automation.

You can automate model discovery, monitoring, and simple inference tasks. For instance, write a cron job that uses `list_models_by_task` to find new models, then uses `run_inference` to test them and logs the performance.

No. Vinkius provides a single endpoint token for the MCP Server. You configure that once in Claude Code, and all authentication with the Hugging Face API is handled on the backend. It keeps your CI secrets clean.

Only the contents of that specific file are sent to the Hugging Face endpoint for the summarization task. The server does not access your environment variables, file system, or any other data on the machine running the script.

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