How to Use the Nyckel ML MCP in VS Code Copilot

Q: Does Nyckel ML support multi-label classification in VS Code Copilot?

Yes, VS Code Copilot can fetch your configuration using getmlfunction to see if your Nyckel ML model is single-label or multi-label, then generate matching code.

Q: How do we check our active Nyckel ML classification endpoints in VS Code Copilot?

Ask the chat panel in VS Code Copilot to run listmlfunctions. It outputs your active Nyckel ML models, complete with their status and unique identifiers.

Share custom machine learning classifiers across your entire engineering team directly inside VS Code Copilot.

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 VS Code Copilot

Create your Vinkius account to connect Nyckel ML to VS Code Copilot 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 VS Code Copilot

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate model integration in VS Code Copilot

By committing a shared configuration file to your repository, your team gets instant access to your active Nyckel ML classifiers through this MCP Server inside VS Code Copilot using `get_ml_function`. Onboarding new developers to your Nyckel ML pipelines is a massive time sink without VS Code Copilot. Developers can ask the VS Code Copilot chat panel to explain how a specific Nyckel ML classifier works. The agent calls `get_ml_function` to retrieve the active labels, ensuring everyone on the team is building against the correct Nyckel ML endpoints inside VS Code Copilot.

Inspect training samples as a team

Your team can query the Nyckel ML training set directly from the terminal panel by asking VS Code Copilot to run `list_ml_samples`. Debugging Nyckel ML classification drift requires looking at what your model actually learned while working in VS Code Copilot. If a developer spots a mislabeled data point in VS Code Copilot, they can run `annotate_ml_sample` to update Nyckel ML through the chat. This updates the global Nyckel ML training set instantly, keeping your team's production models accurate without manual dashboard work in VS Code Copilot.

Search vector databases without SQL

Ask the VS Code Copilot chat agent to run `semantic_search` to test query strings against your Nyckel ML index directly inside the editor. Writing complex vector search queries during development slows down your feature delivery in VS Code Copilot. The returned Nyckel ML matches help your team verify search relevance inside VS Code Copilot before writing database adapters. It saves hours of local database seeding and index configuration for your Nyckel ML project in VS Code Copilot.

Setup guide

Set up Nyckel ML MCP in VS Code Copilot

Prerequisites

VS Code 1.99 or later with GitHub Copilot extension
Active Vinkius subscription with a valid endpoint token

1

Open MCP configuration

Open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and run "MCP: Add Server". Select HTTP (Streamable) as the server type. VS Code will create .vscode/mcp.json in your workspace.
2

Add the Nyckel ML MCP

Paste the JSON snippet shown on the right into your .vscode/mcp.json. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Switch to Agent mode

Open Copilot Chat (Cmd+Shift+I / Ctrl+Shift+I) and switch to Agent mode using the dropdown. MCP tools are only available in Agent mode — they do not appear in Edit or Ask modes.
4

Verify the connection

In the Copilot Chat input, type # to list available tools. You should see the Nyckel ML tools listed. Try asking: "List my recent Nyckel ML transactions" and Copilot will invoke them automatically.

.vscode/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 VS Code Copilot

Create a configuration file in your project root and commit it to Git. Every developer using VS Code Copilot will instantly share access to the exact same Nyckel ML tools using an MCP configuration file.

Yes, developers can collaboratively build datasets. Anyone on the team can run `create_ml_sample` in VS Code Copilot to feed real-world edge cases into Nyckel ML.

Yes, VS Code Copilot can fetch your configuration using `get_ml_function` to see if your Nyckel ML model is single-label or multi-label, then generate matching code.

Ask the chat panel in VS Code Copilot to run `list_ml_functions`. It outputs your active Nyckel ML models, complete with their status and unique identifiers.

Vinkius runs all API calls in secure, transient sandboxes that retain no logs. Your training samples and image classification payloads are routed directly to Nyckel ML with zero local caching.

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