How to Use the Hugging Face Vision MCP in Claude Code

Q: What's the command to connect Claude Code to the Hugging Face Vision MCP server?

Run claude mcp add --transport http hf-vision -- , replacing with the server endpoint from Vinkius. Use claude mcp list to confirm it's connected. Your agent will then have access to the vision tools.

Run Hugging Face vision models from your terminal. Pipe image data to Claude Code for headless classification, detection, and generation.

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 Vision MCP to Claude Code

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Image Processing in Scripts

The `image_classification` tool lets you build shell scripts that sort images based on their content. You can pipe a directory of images to your agent and have it move them into folders like 'cars', 'documents', or 'invoices'. It's a straightforward way to automate file organization that would otherwise be a manual chore. Just point it at a folder and let it run in the background.

Vision Tasks in Your CI/CD Pipeline

Use this MCP server in a GitHub Action or any other CI/CD job. The `text_to_image` tool can generate watermarked images or test assets during a build. There's no need to store these assets in your repo. Or, you can use `object_detection` in a test step to validate that key elements are present in a screenshot of your app. If an icon is missing, the build fails.

Extract Data from Images Headlessly

The `image_to_text` tool is for pulling text or descriptions from images in an automated workflow. You can point it at a monitoring dashboard screenshot to get the latest stats and pipe them to an alerting system. It's also useful for generating summaries for a batch of photos in a script. Your Claude Code agent gets the caption as a string, and you can parse it or save it as metadata.

Setup guide

Set up Hugging Face Vision 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-vision-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http hugging-face-vision-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 Vision 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-vision-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 Vision. 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 Vision 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 Vision MCP in Claude Code

After connecting the server, you can pipe image data (like a base64 string) to your agent. For example: `cat image.jpg | base64 | claude 'caption this image'`. Claude Code will use the `image_to_text` tool automatically.

Run `claude mcp add --transport http hf-vision -- `, replacing `` with the server endpoint from Vinkius. Use `claude mcp list` to confirm it's connected. Your agent will then have access to the vision tools.

Yes. You can write a simple shell script that loops through files in a directory, encodes each one, and pipes it to Claude Code with a prompt. This lets you use tools like `image_classification` or `object_detection` on hundreds of images at once.

You need to send the image as a Base64-encoded string. Most terminal environments have a `base64` command you can use to pipe the file content directly into your prompt.

No. The server processes raw image data (as base64 strings) and text prompts. Each transaction runs in a dedicated, single-use container on Vinkius that is destroyed immediately after execution. This design ensures your data is never persisted.

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