How to Use the Normality Test Engine MCP in Claude

Run exact Jarque-Bera tests locally through Claude Desktop before you ruin your model with non-parametric data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Normality Test Engine MCP to Claude Desktop

Create your Vinkius account to connect Normality Test 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 Normality Test Engine with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Prevent Math Hallucinations in Claude

The `test_normality` tool forces your AI client to execute deterministic Jarque-Bera calculations instead of guessing statistical values. Language models are notorious for hallucinating math when analyzing raw arrays. By delegating the exact computation to this MCP Server, Claude gets the actual skewness and kurtosis metrics returned as hard data. You feed the server a flat list of numeric values. It processes the array through standard statistical logic and hands back the mathematical truth. This completely removes the risk of your agent making up a p-value just because the numbers looked roughly bell-shaped in the prompt.

Validate Assumptions Instantly

Running `test_normality` acts as the mandatory gatekeeper before you commit to a parametric statistical test. You do not want to run an ANOVA on heavily skewed data. Claude checks the distribution shape right in the chat, giving you a clear verdict on whether to proceed or switch to a non-parametric alternative. This MCP integration evaluates the dataset against theoretical normal distributions. If the sample size is moderate and the kurtosis drifts too far from zero, your agent flags the violation immediately. You make the right methodological choice without having to spin up a separate Python environment.

Local Execution via StdIO

Calling `test_normality` happens entirely on your own machine when running the desktop app. You configure the command arguments in your local settings file, and Claude communicates with the server through standard input and output streams. This setup means your raw statistical arrays never bounce through a third-party API just to calculate a simple metric. It runs as a fast, isolated subprocess. You get immediate feedback on your dataset's shape while keeping the computation strictly local.

Setup guide

Set up Normality Test 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 Normality Test 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 Normality Test 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 normality-test-engine-mcp.

json

{
  "mcpServers": {
    "normality-test-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 Normality Test 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 Normality Test Engine MCP in Claude Desktop

Edit your local config file or use the Extensions UI. Add the MCP Server command under the mcpServers key, save, and restart the app. Claude will register the tool immediately.

Yes, if you host the server remotely. Go to Settings, open Integrations, and paste your custom connector URL. Just remember the endpoint cannot be localhost.

Because language models cannot do math reliably. This tool forces Claude to use deterministic code for the Jarque-Bera test. You get real statistics instead of text-prediction guesses.

Stick to moderate sample sizes between 30 and 5,000 data points. Massive datasets trigger rejection on trivial deviations due to the Central Limit Theorem. Small samples lack the statistical power to detect non-normality accurately.

No. Your raw numeric data stays exactly where it is processed. The local stdio connection ensures the statistical evaluation happens on your hardware without transmitting a single integer over the network.

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