How to Use the Hugging Face LLM MCP in Cursor

Q: How do I install the Hugging Face LLM MCP server in Cursor?

Add the server to your .cursor/mcp.json file under the mcpServers key. Make sure your Hugging Face API token is set, then enable Agent mode in your Cursor chat to start invoking the tools.

Q: Where does my source code go when I run these tools?

Only the specific text blocks you pass to tools like summarizetext or fillmask are sent to Hugging Face endpoints. Your local codebase remains completely private, and the MCP server runs in an ephemeral sandbox.

Inject open-source model completions and NLP tools directly into your Cursor editor using the Hugging Face LLM MCP Server.

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 Cursor

Create your Vinkius account to connect Hugging Face LLM 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 LLM with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate text inside Cursor using open-source models

The Hugging Face LLM MCP server provides the `text_generation` tool to pull model completions directly into your Cursor editor. Your agent calls this tool to generate code blocks, comments, or documentation using models like Mistral. Because the tool returns raw text completions, your agent inserts the generated code directly into your active file. This cuts down on copy-pasting and lets you test open-source model outputs in real time.

Classify and analyze text files in Cursor

The `classify_text` tool lets you categorize codebase files, markdown notes, or raw logs using zero-shot classification. Your agent runs this tool alongside `sentiment_analysis` to organize files without manual labeling. This means you can ask Cursor to run a quick sentiment check on a log file or categorize user feedback files. The server outputs structured labels directly into your editor's terminal or chat window.

Extract entities and run masked language tasks

The `extract_entities` tool parses your files to locate people, organizations, and locations. Your agent uses this to clean up metadata or extract key details from raw text documents inside Cursor. Combined with `fill_mask` for completing missing words, these tools give you a fast way to run NLP pipelines. You get structured data from your local files without leaving your coding workspace.

Setup guide

Set up Hugging Face LLM 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 LLM 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 LLM transactions." If the MCP tools are loaded correctly, Cursor will call the Hugging Face LLM tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "hugging-face-llm-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 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 Cursor

Add the server to your `.cursor/mcp.json` file under the `mcpServers` key. Make sure your Hugging Face API token is set, then enable Agent mode in your Cursor chat to start invoking the tools.

Yes, your agent can read local files and pass them to Hugging Face LLM tools like `classify_text` or `extract_entities`. Cursor routes the file contents to the server and prints the structured results in your editor.

You can configure the server to target specific open-source model endpoints for tools like `text_generation`. This allows your Cursor agent to query custom-tuned models hosted on Hugging Face.

If you hit rate limits on free endpoints, the server returns an error. You can upgrade your Hugging Face token or configure your Cursor agent to handle retries for heavy batch tasks.

Only the specific text blocks you pass to tools like `summarize_text` or `fill_mask` are sent to Hugging Face endpoints. Your local codebase remains completely private, and the MCP server runs in an ephemeral sandbox.

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