How to Use the Hugging Face MCP in Cursor

Q: Can Cursor use Hugging Face models for text generation?

Yes, your agent can trigger runtextgeneration during a coding session. It returns raw output you can immediately insert into your project.

Q: Does Hugging Face work with Cursor global config?

Yes, add the server to your global /.cursor/mcp.json file. This makes the tools available in every project you open.

Q: How are inference results handled in Cursor?

The output from runtextclassification or other tools is passed back to the agent. You can then ask the agent to format that data for your code.

Bring Hugging Face models into your Cursor editor. Let your AI agent write code that actually calls live inference endpoints.

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 Cursor

Create your Vinkius account to connect Hugging Face to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time model discovery

Stop guessing which model to use. Let your Cursor agent run `list_models` to find the latest versions based on downloads or specific tasks. This gives your agent the exact model ID needed for your code. It cuts out the manual search process entirely.

Inject inference into code

Your agent can call `run_inference` directly while writing your application logic. It uses the real API response to build your features. This creates working code on the first try. You get concrete data structures instead of placeholder comments.

Check repository metadata

Query `get_space` or `get_dataset` to understand the dependencies of your project. Your agent pulls this data into the chat to help you debug integration issues. It keeps your context window accurate. You have all the information you need right next to your source files.

Setup guide

Set up Hugging Face MCP in Cursor

Prerequisites

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

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Hugging Face MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Hugging Face transactions." If the MCP tools are loaded correctly, Cursor will call the Hugging Face tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.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 Cursor

Create an mcp.json file in your project or global directory. Add the server configuration there and enable Agent mode in your chat.

Yes, your agent can trigger `run_text_generation` during a coding session. It returns raw output you can immediately insert into your project.

Yes, add the server to your global ~/.cursor/mcp.json file. This makes the tools available in every project you open.

The output from `run_text_classification` or other tools is passed back to the agent. You can then ask the agent to format that data for your code.

The server only touches public model data and the specific text strings you send for inference. Your local files are never uploaded unless you explicitly include them in the prompt.

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