How to Use the Hugging Face MCP in Windsurf

Q: How does Windsurf use Hugging Face to find models?

Windsurf's Cascade agent uses tools like listmodels and listmodelsbytask to query the Hugging Face Hub. You just state your goal, and it finds matching models based on your criteria, no manual searching needed.

Q: Can I run any model from the Hub?

Yes, with the runinference tool. As long as the model has a public inference API on Hugging Face, Windsurf can send a request and get the output for you right in the editor.

Let Windsurf's Cascade agent find, test, and report on Hugging Face models for you, all from a single prompt.

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 Windsurf

Create your Vinkius account to connect Hugging Face to Windsurf 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 Windsurf

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Find the Right Model, Instantly

Tell Windsurf's Cascade agent what you're trying to do, and it will use the Hugging Face tools to find the best models. It can `list_models_by_task` to see top performers for summarization, then `get_model` to pull the specifics for each one. Cascade doesn't just list them; it can chain these actions. For example, ask it to "find three summarization models and get their details," and it runs the sequence automatically. You get a clean report without prompting each step.

Run Inference Inside Windsurf

This MCP Server connects Hugging Face inference directly to your editor. You can highlight a block of text and ask Windsurf to use `run_summarization` or `run_text_classification` on it. The results appear right where you're working. Because Cascade is autonomous, you can give it more complex goals. "Summarize this article, then generate a new title for it." Cascade will chain `run_summarization` and `run_text_generation` without you needing to copy and paste the output between steps.

Inspect Datasets and Spaces

The server isn't just for models. You can ask Windsurf to `list_datasets` to find training data or `list_spaces` to see live demos. It's a fast way to check what's available on the Hub. This is great for research. Tell Cascade to "find datasets for sentiment analysis and list their details." It will use `list_datasets` and `get_dataset` in a chain, giving you the information you need to decide which data to use for your next project.

Setup guide

Set up Hugging Face MCP in Windsurf

Prerequisites

Windsurf IDE installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Click the Cascade assistant icon in the sidebar, then click the hammer icon (🔨) at the top of the panel. Select "Configure" to open ~/.codeium/windsurf/mcp_config.json.
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

Refresh MCPs

Go back to the hammer icon (🔨) in Cascade and click "Refresh". Windsurf will detect the new server. No full restart is needed — the connection is hot-reloaded.
4

Verify in Cascade

Start a new Cascade conversation and ask something like "Show my Hugging Face payment history." If connected, Cascade will call the Hugging Face tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.json

{
  "mcpServers": {
    "hugging-face-alternative-mcp": {
      "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 Windsurf

Windsurf's Cascade agent uses tools like `list_models` and `list_models_by_task` to query the Hugging Face Hub. You just state your goal, and it finds matching models based on your criteria, no manual searching needed.

Yes, with the `run_inference` tool. As long as the model has a public inference API on Hugging Face, Windsurf can send a request and get the output for you right in the editor.

The main benefit is automation. Windsurf's Cascade agent can chain multiple Hugging Face tools together to complete a task, like finding a model with `list_models` and then testing it with `run_text_generation`, all from a single instruction.

No, Vinkius manages the connection. You just add the Hugging Face MCP Server to Windsurf, and your requests are securely proxied. You don't handle the API key directly in your client.

Only the specific input you provide for an inference task is sent. If you use `run_summarization`, only the text you selected for summarization is transmitted. Your code, project files, and other editor context are never sent.

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