How to Use the Normality Test Engine MCP in CrewAI

Q: How do I configure the Normality Test Engine for a specific CrewAI agent?

You pass the hosted server URL directly to the agent's mcps parameter during initialization. This grants that specific agent exclusive access to the testnormality tool, allowing it to act as the dedicated statistical validator for the rest of your crew.

Q: How do my agents share the kurtosis and skewness results?

Once an agent runs the testnormality tool, the resulting metrics are stored in CrewAI's short-term shared memory. This allows other agents in the crew to read the skewness and kurtosis values instantly, preventing duplicate tool runs and keeping the workflow efficient.

Q: How is my research data secured when CrewAI calls the Normality Test Engine?

All numeric arrays sent by your CrewAI agents to the testnormality tool are processed in isolated, single-use containers on Vinkius. The data is parsed, the Jarque-Bera test is executed, the results are returned, and the container is destroyed, leaving no trace of your proprietary statistical data behind.

Equip your CrewAI agent teams with deterministic statistical verification to run autonomous, bias-free data analysis 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 CrewAI

Create your Vinkius account to connect Normality Test Engine to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign statistical validation to specialized CrewAI agents

Build a multi-agent team where a dedicated Data Analyst agent is solely responsible for checking distribution assumptions. By connecting this MCP Server to CrewAI, you give that agent the exact tool it needs to verify mathematical assumptions before passing data to the Researcher agent. The Data Analyst agent calls the `test_normality` tool to calculate skewness and kurtosis. Once verified, the agent writes the results to shared memory, allowing the downstream Writer agent to draft reports with mathematically sound conclusions.

Implement hierarchical quality control with this MCP Server

In a complex CrewAI setup, a Manager agent can oversee several analyst agents working on different datasets. You can configure the `test_normality` tool as a mandatory quality gate that every dataset must pass before any parametric analysis is approved. If an analyst agent attempts to run a t-test on skewed data, the Manager agent catches the error using the Jarque-Bera metrics returned by the tool. The crew then automatically shifts to non-parametric testing, keeping the entire operation autonomous and accurate.

Eliminate mathematical hallucinations across your CrewAI teams

When multiple agents collaborate, errors can compound if one agent guesses at the shape of a dataset. This MCP Server ensures that every agent in your crew relies on the same deterministic, local python-based calculations instead of LLM approximations. By forcing your crew to call the `test_normality` tool, you guarantee that skewness and kurtosis are calculated using exact formulas. Always run `test_normality` first because math does not lie, and guessing distribution shapes ruins your downstream analysis.

Setup guide

Set up Normality Test Engine MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Normality Test Engine tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Normality Test Engine Analyst",
    goal="Access and analyze Normality Test Engine data via MCP.",
    backstory="Expert analyst with direct Normality Test Engine access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Normality Test Engine transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Normality Test Engine Analyst",
        goal="Access and analyze Normality Test Engine data via MCP.",
        backstory="Expert analyst with direct Normality Test Engine access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Normality Test Engine transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

You pass the hosted server URL directly to the agent's `mcps` parameter during initialization. This grants that specific agent exclusive access to the `test_normality` tool, allowing it to act as the dedicated statistical validator for the rest of your crew.

Yes, the Vinkius infrastructure handles concurrent requests easily. Multiple agents within your crew can call the `test_normality` tool at the same time to analyze different columns of a dataset, accelerating your parallel data processing pipelines.

Writing custom python execution scripts inside CrewAI agents requires maintaining local environments, managing dependencies, and dealing with security risks. This MCP Server provides a pre-built, zero-trust sandbox to run the `test_normality` tool securely without writing a single line of boilerplate code.

Once an agent runs the `test_normality` tool, the resulting metrics are stored in CrewAI's short-term shared memory. This allows other agents in the crew to read the skewness and kurtosis values instantly, preventing duplicate tool runs and keeping the workflow efficient.

All numeric arrays sent by your CrewAI agents to the `test_normality` tool are processed in isolated, single-use containers on Vinkius. The data is parsed, the Jarque-Bera test is executed, the results are returned, and the container is destroyed, leaving no trace of your proprietary statistical data 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