How to Use the Hugging Face MCP in Vercel AI SDK

Q: How does the Hugging Face MCP Server handle token usage with Vercel AI SDK?

You pass your Hugging Face API token through the getuser tool configuration inside your server setup. The Vercel AI SDK then securely communicates with the Hub via the Vinkius gateway, keeping your credentials hidden from the client browser.

Q: Can I stream Hugging Face Space metadata using Vercel AI SDK?

Yes. The getspace tool retrieves active SDK types like Gradio or Streamlit and streams them directly into your UI. Your Vercel AI SDK agent displays the live configuration details without waiting for a full payload download.

Q: Can my agent search both models and datasets?

Absolutely. Your agent calls listmodels and listdatasets in parallel to gather metadata from both Hub registries.

Stream Hugging Face model and dataset metadata directly into your React components with Vercel AI SDK.

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 Vercel AI SDK

Create your Vinkius account to connect Hugging Face to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Hugging Face model files directly to your UI

The `list_model_files` tool lets your Vercel AI SDK client inspect repository structures and display model artifacts instantly. Instead of making users wait for a full API response, this MCP Server streams the file tree directly into your Next.js frontend as the agent discovers it. You use `get_model_tags` alongside it to render framework badges like PyTorch or Safetensors in real-time. This keeps your interface fast and responsive without blocking the main thread.

Render interactive dataset tables as they stream

The `list_datasets` and `list_dataset_files` tools feed raw repository data straight into your streaming UI components. Your agent queries the Hub and immediately lists files like `train.parquet` or `README.md` while the user watches. By coupling this with `get_space`, you display live Hugging Face Space configurations directly inside your React layout. The Vercel AI SDK handles the stream, rendering each piece of Space metadata the moment it arrives.

Build live discussion feeds with Vercel AI SDK

The `list_model_discussions` tool pulls active community threads for any model directly into your agent's context. Your application displays these active bug reports and feature requests instantly, allowing users to monitor repository health on the fly. If a user wants to report an issue, the agent uses `create_discussion` to open a new thread on the Hub. The Vercel AI SDK streams the resulting discussion URL straight to the chat UI for immediate access.

Setup guide

Set up Hugging Face MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all Hugging Face tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent Hugging Face transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

You pass your Hugging Face API token through the `get_user` tool configuration inside your server setup. The Vercel AI SDK then securely communicates with the Hub via the Vinkius gateway, keeping your credentials hidden from the client browser.

Yes. The `get_space` tool retrieves active SDK types like Gradio or Streamlit and streams them directly into your UI. Your Vercel AI SDK agent displays the live configuration details without waiting for a full payload download.

This server runs inside a V8 sandbox on Vinkius, which optimizes network requests to the Hub. When Vercel AI SDK triggers multiple `list_models` queries, the gateway manages the connection to prevent API throttling.

Absolutely. Your agent calls `list_models` and `list_datasets` in parallel to gather metadata from both Hub registries.

The Vinkius MCP Server isolates your Hugging Face credentials and repository metadata in an ephemeral environment. No API tokens or raw repository layouts are ever stored on disk, ensuring your private Hub access remains fully sandboxed.

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