How to Use the Nyckel ML MCP in Windsurf

Train, test, and run machine learning classification models directly inside Windsurf without writing boilerplate API code.

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 Windsurf

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated model training inside Windsurf

The `create_ml_sample` tool lets Cascade send new data points straight to your classification pipeline. This means your agent can watch your codebase for new data inputs and feed them directly into your training set without manual exports. Once uploaded, the agent uses `annotate_ml_sample` to assign the correct labels instantly. You don't need to log into a separate web dashboard to organize your training data because your IDE handles the entire labeling pipeline on the fly.

Real-time classification and search

The `invoke_ml_function` tool runs immediate classification queries against your active models directly from Cascade. This allows your agent to test model predictions on local files or live inputs during your development loop. For unstructured text queries, the `semantic_search` tool finds the closest matching samples in your index. This turns your raw training data into an active, searchable database that your IDE can query to find similar patterns.

Active pipeline monitoring

The `list_ml_functions` tool retrieves the status of all active classifiers in your account. Your agent checks this list to verify endpoints before attempting to run predictions or edit labels. If a model becomes obsolete, the agent uses `delete_ml_function` to clean up your workspace. This keeps your active endpoints organized, and you can verify the remaining configurations using `get_ml_function` at any point.

Setup guide

Set up Nyckel ML 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 Nyckel ML 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 Nyckel ML payment history." If connected, Cascade will call the Nyckel ML tools directly. You will see a green dot next to the server name in the MCP panel.

mcp_config.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 Windsurf

Open your settings and add the server configuration under the mcpServers key. Once you hit refresh, Cascade instantly detects the toolset and starts using it. This MCP server connects your project to your classification endpoints with zero manual setup.

Yes, Cascade handles this by chaining tools. The agent reads your local files, uploads them, and applies the correct tags via the MCP Server. You just tell the agent which folder to process.

You ask Cascade to test a specific input. The MCP connection sends the text or image straight to your active model and returns the predicted label in seconds.

Ask the agent to find and remove inactive pipelines. It will list your active endpoints and delete the ones you no longer use.

All text and image samples sent through the tools go directly to Nyckel's API endpoints. Vinkius runs this integration in an isolated, secure sandbox that destroys your session data the moment you disconnect. No training data is cached or stored on the Vinkius platform.

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