ClaudeChatGPTPerplexityGeminiMicrosoft CopilotRaycastMeta AIGrokZ.aiQwenKimi
DeepSeekMistralCursorVS CodeWindsurfJetBrainsClineLovableVercel AI SDKLangChain

Use Nyckel with your AI.

Connect your account once and let the AI you already use work with it, without building another integration. Classify data and perform semantic search via Nyckel. track ML functions, samples, and labels directly from your AI agent.

Included with plan

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Complete set · 10 capabilities

The complete Nyckel capability set.

These are the exact actions your AI can choose when you ask it to work with Nyckel.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through Nyckel.

  1. 01

    Create ml sample

    Add a training sample

  2. 02

    Delete ml function

    Delete an ML function

  3. 03

    Get ml function

    Get specific function info

  4. 04

    Get account info

    Get current account info

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through Nyckel.

  1. 05

    List ml functions

    ) in your account. List all ML functions

  2. 06

    List ml samples

    List training samples

  3. 07

    Annotate ml sample

    Assign label to a sample

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through Nyckel.

  1. 08

    Invoke ml function

    Classify data using a function

  2. 09

    List ml labels

    List available labels

  3. 10

    Semantic search

    Perform semantic search

Observed, not estimated

885ms average. Fast in production.

Nyckel is checked daily against the live service.

Daily averagePeak 1036ms
Aug 20Today
Fastest day
699ms
Slowest day
1036ms
14-day trend
Slowing+19%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Nyckel, so you can see the experience inside your AI.

It does not authenticate your account with Nyckel. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Nyckel Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_XHJXGFWpxs8iH5SOEbAtipKgPVXhxGte0LRcKzdL/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Nyckel capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "nyckel-ml-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_XHJXGFWpxs8iH5SOEbAtipKgPVXhxGte0LRcKzdL/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

FAQ

Questions Nyckel owners ask.

  • 01

    How do I get my Nyckel credentials?

    Log in to your Nyckel dashboard, navigate to your profile or settings, and look for the 'API Keys' section to find your Client ID and Client Secret.

  • 02

    Does this support image classification?

    Yes! You can pass a publicly accessible image URL to the invoke_ml_function or semantic_search capabilities to classify or search based on visual content.

  • 03

    How accurate are the predictions?

    Accuracy depends on the quality and quantity of training samples provided to your Nyckel function. The invoke_ml_function capability returns a confidence score for each prediction.