How to Use the Normality Test Engine MCP in Mastra AI

Q: Can I require human approval before running a Normality Test Engine check in Mastra AI?

Yes, you can use Mastra's requireToolApproval setting on the testnormality tool. This pauses the workflow and prompts a human reviewer to approve the dataset size and parameters before running the Jarque-Bera calculation, preventing wasted computational resources on massive datasets.

Q: What happens if the data passed to the MCP Server is empty?

The testnormality tool will return a clear statistical error instead of failing silently. Your Mastra AI workflow can catch this error using its built-in error handling blocks, allowing the agent to request a valid numeric dataset from the user without crashing the pipeline.

Q: How does the Normality Test Engine protect my proprietary numeric data in Mastra AI?

The numeric arrays processed by the testnormality tool are evaluated in an isolated, ephemeral V8 sandbox on Vinkius. No data is written to persistent disks or shared with external APIs, ensuring your proprietary research metrics remain entirely confidential throughout the workflow execution.

Build fail-safe statistical validation workflows in Mastra AI by running deterministic normality checks before executing parametric pipelines.

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 Mastra AI

Create your Vinkius account to connect Normality Test Engine to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Branch your Mastra AI workflows based on data distribution

Stop hardcoding your data pipelines to assume normality. By integrating this MCP Server with Mastra AI, you can build a workflow that runs the `test_normality` tool first, then uses conditional branching to select the correct downstream statistical test. If the skewness metrics indicate non-normal data, your Mastra workflow automatically routes the dataset to a non-parametric alternative like a Wilcoxon test. If it passes, the workflow branches to a standard t-test, ensuring mathematical integrity without manual intervention.

Automated retries for noisy datasets in Mastra AI

Dirty data can throw off kurtosis checks and stall your automated analysis. When your agent calls the `test_normality` tool, Mastra AI handles transient errors or data format anomalies with built-in exponential backoff. If a dataset fails validation due to formatting, the workflow triggers a cleanup step and retries the normality check. This keeps your autonomous statistical pipelines running smoothly even when dealing with unpredictable raw inputs.

Deploy statistical guardrails using this MCP Server

Running parametric models on skewed data leads to false discoveries. You can deploy this MCP Server alongside your Mastra AI agents to act as a strict gatekeeper for all incoming experimental data. The agent executes the `test_normality` tool as a mandatory pre-flight check. If the data fails the Jarque-Bera threshold, the workflow halts. Always run `test_normality` first because math does not lie.

Setup guide

Set up Normality Test Engine MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Normality Test Engine tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "normality-test-engine-mcp-client",
  servers: {
    "normality-test-engine-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Normality Test Engine Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Normality Test Engine tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Normality Test Engine transactions"
);
console.log(result.text);

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 Mastra AI

Instantiate the MCPClient with the server URL, retrieve the `test_normality` tool, and register it directly inside your Mastra agent's tool array. You can then reference the tool's output in your workflow steps to branch your logic based on the returned skewness and kurtosis values.

Writing custom pandas or scipy scripts inside your agent workflows adds maintenance overhead and deployment complexity. This MCP Server provides a pre-configured, zero-setup environment to run the `test_normality` tool, allowing your TypeScript-native Mastra agents to execute python-grade statistical tests instantly.

Yes, you can use Mastra's `requireToolApproval` setting on the `test_normality` tool. This pauses the workflow and prompts a human reviewer to approve the dataset size and parameters before running the Jarque-Bera calculation, preventing wasted computational resources on massive datasets.

The `test_normality` tool will return a clear statistical error instead of failing silently. Your Mastra AI workflow can catch this error using its built-in error handling blocks, allowing the agent to request a valid numeric dataset from the user without crashing the pipeline.

The numeric arrays processed by the `test_normality` tool are evaluated in an isolated, ephemeral V8 sandbox on Vinkius. No data is written to persistent disks or shared with external APIs, ensuring your proprietary research metrics remain entirely confidential throughout the workflow execution.

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