How to Use the Feature Scaler Engine MCP in Claude

Q: How do I configure Feature Scaler Engine in my Claude Desktop configuration?

Open your claudedesktopconfig.json file and add the server configuration under the mcpServers key. Point it to the command provided by Vinkius, restart your Claude Desktop app, and the scalefeatures tool will show up under the hammer icon.

Q: Can Feature Scaler Engine scale CSV files on my drive using Claude Desktop?

Yes. When running on Claude Desktop, the scalefeatures tool reads numeric columns directly from your local hard drive, processes them, and writes the standardized data back to your workspace.

Q: How does this MCP Server handle zero-variance columns in my datasets?

It runs a built-in safety check. If the scalefeatures tool detects a column where all numbers are identical, it prevents division-by-zero errors and alerts your desktop agent.

Q: Is my numeric dataset private when using Feature Scaler Engine?

Absolutely, because all math runs locally. The scalefeatures tool processes your numeric columns and arrays on your own hardware, so your raw data never leaves the Claude Desktop sandbox.

Get raw numbers in your local files perfectly scaled directly from your Claude Desktop app.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Feature Scaler Engine MCP to Claude Desktop

Create your Vinkius account to connect Feature Scaler Engine to Claude Desktop 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 Feature Scaler Engine with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Local Dataset Normalization inside Claude Desktop

Stop copying massive columns of unscaled numbers into external Python scripts just to run a standard Z-score. This MCP Server lets your local Claude Desktop run math directly on your numeric datasets without sending raw data to third parties. You tell the agent which CSV or local matrix needs processing, and it runs the scaling operation instantly. The server triggers the `scale_features` tool on your local machine to process the values. It applies exact Z-Score or MinMax math on your physical drive, returning clean, normalized arrays straight into your chat session.

Direct Local Scaling for Neural Net Prep

Preparing data for local training runs requires clean inputs, and this MCP Server handles the math right where your files live. Your desktop agent reads the raw columns, runs the numbers through the `scale_features` tool, and writes the scaled values back to your local directory. You do not need to boot up a heavy Jupyter Notebook just to scale a few test columns. The Claude Desktop app talks directly to this local process to handle zero-variance checks and output clean distributions.

Zero-Latency Local Normalization

This MCP Server runs entirely inside a local V8 sandbox on your machine, avoiding any network lag. When you tell Claude Desktop to normalize a dataset, the `scale_features` tool executes in milliseconds. There are no remote API endpoints to wait for or pay for. It reads the local file, runs the Z-score calculation, and hands the scaled array back to your chat window instantly.

Setup guide

Set up Feature Scaler Engine MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Feature Scaler Engine MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Feature Scaler Engine MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under feature-scaler-engine-mcp.

json

{
  "mcpServers": {
    "feature-scaler-engine-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 simple-statistics. 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 Feature Scaler Engine 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 Feature Scaler Engine MCP in Claude Desktop

Open your `claude_desktop_config.json` file and add the server configuration under the `mcpServers` key. Point it to the command provided by Vinkius, restart your Claude Desktop app, and the `scale_features` tool will show up under the hammer icon.

Yes. When running on Claude Desktop, the `scale_features` tool reads numeric columns directly from your local hard drive, processes them, and writes the standardized data back to your workspace.

Yes, you can specify MinMax scaling directly through the chat input. The `scale_features` tool maps your numeric array values to a strict zero-to-one range without leaving your local environment.

It runs a built-in safety check. If the `scale_features` tool detects a column where all numbers are identical, it prevents division-by-zero errors and alerts your desktop agent.

Absolutely, because all math runs locally. The `scale_features` tool processes your numeric columns and arrays on your own hardware, so your raw data never leaves the Claude Desktop sandbox.

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