4,500+ servers built on MCP Fusion
Vinkius
Nyckel ML logo
Vinkius
Claude Code logo

How to Use the Nyckel ML MCP in Claude Code

Run ML classification and semantic search directly from your terminal using Claude Code to automate your data pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Nyckel ML MCP on Cursor AI Code Editor MCP Client Nyckel ML MCP on Claude Desktop App MCP Integration Nyckel ML MCP on OpenAI Agents SDK MCP Compatible Nyckel ML MCP on Visual Studio Code MCP Extension Client Nyckel ML MCP on GitHub Copilot AI Agent MCP Integration Nyckel ML MCP on Google Gemini AI MCP Integration Nyckel ML MCP on Lovable AI Development MCP Client Nyckel ML MCP on Mistral AI Agents MCP Compatible Nyckel ML MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Claude Code

Connect Nyckel ML MCP to Claude Code

Create your Vinkius account to connect Nyckel ML to Claude Code 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

Command-line model execution with Claude Code

The `invoke_ml_function` tool classifies text or image inputs directly from your terminal session. Claude Code runs this tool to test predictions on live logs or local files without requiring a graphical interface. You can pipe terminal outputs directly into this command to verify how your active models handle real-world server logs or user inputs in real time.

Automated pipeline management

The `list_ml_functions` tool outputs all active classifiers associated with your account. Your terminal agent uses this to map out available endpoints before running automated scripts or CI tasks. When a model is no longer needed, the agent runs `delete_ml_function` to remove the endpoint. This keeps your cloud resources clean and prevents accidental calls to deprecated models.

Terminal-based data ingestion

The `create_ml_sample` tool uploads new training data directly from your shell environment. This allows Claude Code to import local logs or scraped datasets into your training pipeline with a single terminal command. Once uploaded, the agent applies the correct tags using `annotate_ml_sample` to prepare the data for training. This lets you build and update models using cron jobs or terminal scripts.

Setup guide

Set up Nyckel ML MCP in Claude Code

Prerequisites

  • Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
  • Active Vinkius subscription with a valid endpoint token
  1. 1

    Run the add command

    Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.

  2. 2

    Verify the connection

    Start a Claude Code session and type /mcp to list connected servers. You should see nyckel-ml-mcp with a green status indicator.

  3. 3

    Start using tools

    Ask Claude Code something like "Check my latest Nyckel ML transactions." It will automatically discover and invoke the available Nyckel ML tools.

Terminal
claude mcp add --transport http nyckel-ml-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

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 Claude Code

Run the add command with the transport flag and your server URL. Your CLI agent will verify the connection and list the new commands right away. This MCP Server setup works across any standard shell environment.
Yes, you can instruct the terminal agent to loop through a directory of local files. The MCP connection will process each file sequentially and output the results back to your console.
Ask the agent to search your dataset for specific concepts. It sends your query via the MCP Server and prints the closest matching samples directly in your terminal window.
Run a query asking for your active functions. The agent will list all deployed models, their input types, and their current status in a clean terminal table.
Your data payloads travel over an encrypted connection straight to Nyckel's servers. The Vinkius runtime executes each command in a secure, single-tenant environment that instantly purges your inputs upon completion. Your raw assets never persist on our host infrastructure.

Start using the Nyckel ML MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 10 tools

We've already built the connector for Nyckel ML. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.