How to Use the Hugging Face LLM MCP in Claude Code

Q: How can I use the Hugging Face LLM in a GitHub Action with Claude Code?

First, add the server using the claude mcp add command and store your Vinkius token as a repository secret. In your workflow YAML, you can then pipe text to Claude Code to use any tool, like classifytext, as part of your CI pipeline.

Q: What's the command to add the Hugging Face LLM server to Claude Code?

The command is claude mcp add --transport http -- . Replace with a local alias and with the endpoint Vinkius provides. Use claude mcp list to check that it was added.

Pipe text to Claude Code and use Hugging Face models for analysis, translation, and generation in any shell script or CI/CD pipeline.

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 LLM MCP to Claude Code

Create your Vinkius account to connect Hugging Face LLM 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 LLM with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

NLP Tools for Your Terminal

This server adds eight text-processing tools to Claude Code. It's built for the command line. You can pipe data directly to your agent and have it perform an action, like running `sentiment_analysis` on a log file. For example: `cat customer_feedback.log | claude run sentiment_analysis`. The output is clean text, ready to be piped to other standard unix tools like `grep` or `jq`. It becomes just another command in your toolchain.

Batch Processing with an MCP Server

Automate your text workflows. Write a simple shell script that loops through a directory of documents, feeding each one to Claude Code to run `summarize_text` or `translate_text`. This is the right way to handle batch jobs without a complex UI. It’s ideal for cron jobs that process daily reports or for running analysis across a whole dataset from your terminal.

Headless Text Generation

Use `text_generation` in a completely non-interactive way. Your build script can call Claude Code to generate boilerplate code, create config files from a template, or even draft release notes based on your git log. Because Claude Code is headless, you can integrate text generation into any automated process. It runs quietly in a Docker container, a GitHub Action, or a simple cron job.

Setup guide

Set up Hugging Face LLM 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-llm-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http hugging-face-llm-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 LLM 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-llm-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 LLM. 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 LLM 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 LLM MCP in Claude Code

First, add the server using the `claude mcp add` command and store your Vinkius token as a repository secret. In your workflow YAML, you can then pipe text to Claude Code to use any tool, like `classify_text`, as part of your CI pipeline.

The command is `claude mcp add --transport http -- `. Replace `` with a local alias and `` with the endpoint Vinkius provides. Use `claude mcp list` to check that it was added.

Yes. While HTTP is common for remote servers, this MCP server works with `stdio`, `http`, and `sse` transports in Claude Code. You can specify the transport that best fits your script or environment.

Your Hugging Face token should be set as an environment variable (`HF_TOKEN`) in your CI/CD environment. The Vinkius-managed server will pick it up automatically to authenticate its requests to the Hugging Face API.

Only the source text for translation is ever sent. It passes through a zero-trust, ephemeral Vinkius environment directly to the Hugging Face API endpoint for the translation model. No data is logged or stored.

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