How to Use the Feature Scaler Engine MCP in Claude Code

Q: Can I use Feature Scaler Engine in automated shell scripts with Claude Code?

Yes, the scalefeatures tool is fully compatible with headless execution in Claude Code. You can script the CLI agent to read raw numeric logs, scale them, and output the results without manual prompts.

Q: Does Feature Scaler Engine support standard input piping in Claude Code?

The scalefeatures tool processes structured numerical data passed by Claude Code. Your CLI agent can read standard input, format it, and send it to the server to return clean, scaled metrics.

Scale raw numeric columns directly from your terminal using Claude Code to run mathematical transformations.

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 Code

Create your Vinkius account to connect Feature Scaler Engine 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

Setup Feature Scaler Engine with Claude Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Headless data prep via this MCP Server

Run `scale_features` straight from your command line to normalize massive datasets without opening a GUI. Claude Code executes the scaling logic, pipes the output to your terminal, and lets you redirect it to downstream scripts. This setup is perfect for automated CI/CD pipelines and cron jobs where you need to clean incoming metrics. You get deterministic, local mathematical scaling without the overhead of heavy data science notebooks.

Deterministic scaling for terminal pipelines

By calling the `scale_features` tool, Claude Code applies Z-score standardization to your numeric inputs. The tool calculates the exact mean and standard deviation of your terminal inputs, returning normalized values. You can feed raw numbers directly from standard input, let the server process them, and pipe the clean output straight into your training scripts. It removes the need to write custom preprocessing boilerplate in your production code.

Fast MinMax normalization in Claude Code

When your neural networks require bounded inputs, Claude Code uses the `scale_features` tool to map features to a strict zero-to-one range. The math happens locally, ensuring low latency and high throughput for terminal execution. Integrating this MCP Server takes a single terminal command. Once connected, your CLI agent can format and scale numeric arrays on demand, keeping your automated pipelines fast and clean.

Setup guide

Set up Feature Scaler Engine 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

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

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see feature-scaler-engine-mcp with a green status indicator.
3

Start using tools

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

Terminal

claude mcp add --transport http feature-scaler-engine-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the Feature Scaler Engine 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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "feature-scaler-engine-mcp": {
      "type": "url",
      "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 Code

Run the claude mcp add command with the HTTP transport flag and your endpoint URL. Claude Code will save the configuration in your local settings file and instantly register the scaling tools for your CLI sessions.

Yes, the `scale_features` tool is fully compatible with headless execution in Claude Code. You can script the CLI agent to read raw numeric logs, scale them, and output the results without manual prompts.

The `scale_features` tool processes structured numerical data passed by Claude Code. Your CLI agent can read standard input, format it, and send it to the server to return clean, scaled metrics.

You can choose between Z-score standardization and MinMax scaling. The tool applies these transformations deterministically, ensuring that your training data matches your production data perfectly.

All scaling calculations happen inside our isolated, ephemeral V8 sandbox. Your numeric columns are processed in memory and immediately destroyed once the terminal command completes, leaving no trace behind.

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