How to Use the Nyckel ML MCP in Cursor

Q: Can I use Nyckel ML to generate typed schemas in Cursor?

Yes, Cursor can call getmlfunction to pull your active Nyckel ML schema. It then writes TypeScript interfaces based on your live classification outputs.

Build intelligent, auto-classifying code inside Cursor by letting your AI agent query and train your models on the fly.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nyckel ML MCP to Cursor

Create your Vinkius account to connect Nyckel ML 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 Nyckel ML with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Generate code in Cursor using live model outputs

When you write code in Cursor, your agent runs `invoke_ml_function` to fetch real, live predictions from Nyckel ML and structures your TypeScript or Python types based on actual API responses. Stop hardcoding mock classification payloads in your Cursor test suites. This active Cursor integration ensures your application code matches the exact output schema of your Nyckel ML classifiers. You get working integration code inside Cursor on the first try without copying JSON payloads back and forth from the Nyckel ML dashboard.

Manage ML functions from your editor

With this MCP Server active, just highlight a list of categories in your Cursor code and ask Cursor to spin up a new Nyckel ML model using `list_ml_functions`. Creating new classification pipelines usually requires switching from Cursor to a web browser. The Cursor editor executes `list_ml_functions` to check your current Nyckel ML setup, then builds or updates your targets. You can clean up old Nyckel ML experiments by triggering `delete_ml_function` directly from the Cursor chat sidebar.

Debug dataset gaps during development

The agent calls `list_ml_samples` to pull down the exact inputs that trained your active Nyckel ML classifier directly into your Cursor editor. When your local Cursor tests fail on edge cases, use Cursor to inspect your Nyckel ML training set. If you find missing edge cases in Cursor, tell the editor to run `create_ml_sample` with the problematic payload to update your Nyckel ML dataset. Your Nyckel ML model retrains instantly, letting you verify the fix in your local Cursor code immediately.

Setup guide

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

.cursor/mcp.json

{
  "mcpServers": {
    "nyckel-ml-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 Nyckel. 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 Nyckel ML 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 Nyckel ML MCP in Cursor

Yes, Cursor can call `get_ml_function` to pull your active Nyckel ML schema. It then writes TypeScript interfaces based on your live classification outputs.

Ask Cursor to find similar code comments or text assets. The agent triggers `semantic_search` to match your local files against your remote Nyckel ML vector index.

Vinkius handles the OAuth handshake, so you only need one endpoint token. Put this token in your Cursor configuration file to connect to Nyckel ML.

Yes, you can manage your clean-up tasks easily. Ask Cursor to run `delete_ml_function` on any inactive Nyckel ML model to keep your account organized.

Every request executes inside an ephemeral V8 sandbox that isolates your inputs. Your custom ML functions and text training data are transmitted directly to Nyckel ML over encrypted channels.

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