How to Use the Normality Test Engine MCP in AutoGen

Arm your AutoGen agents for statistical debates. One agent checks for normality, another challenges the findings.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fuel Multi-Agent Debates

This isn't just a tool; it's evidence for a debate. You can have a 'Statistician' agent call `test_normality` and present the skewness and kurtosis metrics to the group conversation. Then, a 'Pragmatist' agent can challenge the findings. It might argue that even with a non-normal result, the sample size is large enough for the Central Limit Theorem to apply. The tool provides the objective numbers that kickstart the negotiation between your agents.

Consensus-Driven Analysis

With AutoGen, you're not building a simple script. You're orchestrating a conversation. Your agents use the output of `test_normality` to collectively decide on the right statistical model. This approach avoids the pitfalls of a single agent making a critical error. By forcing a debate over the data's distribution, the agent group converges on a more robust and defensible conclusion. This MCP server provides the facts for that debate.

Specialized Agents, One MCP Tool

Design a team of digital specialists. One agent's entire job is to be the 'Validator,' running checks with the `test_normality` tool and reporting its findings back to the group. This mirrors how a real data science team works. The Validator agent provides the data quality report, an 'Analyst' agent proposes a model based on it, and a 'Reviewer' agent can critique the choice. It enables a clear separation of concerns within your multi-agent system.

Setup guide

Set up Normality Test Engine MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Normality Test Engine tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Normality Test Engine_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Normality Test Engine data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

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

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Normality Test Engine_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Normality Test Engine data")
    print(result.messages[-1].content)

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 AutoGen

You'd create two agents. One agent is given the Normality Test Engine tool and a prompt to check data quality. The second agent is prompted to act as a pragmatic reviewer, questioning if deviations from normality are practically significant. The first agent's tool output becomes the input for their conversation.

No, it returns the raw skewness and kurtosis statistics. This is crucial for AutoGen, as the numbers themselves provide rich context for a nuanced debate between agents, rather than a simple binary outcome.

The Normality Test Engine is a managed, secure tool that AutoGen agents can call reliably without complex setup. It allows you to cleanly separate the 'skill' of normality testing from the agent's core logic, making your multi-agent conversations more modular and easier to manage.

Yes, that's the core workflow. One agent calls the Normality Test Engine tool, and its output is posted as a message in the group chat. All other agents in the conversation can then read and react to those statistical results.

The server only sees the numeric data array required for the Jarque-Bera test. The Vinkius platform ensures each request is handled in a completely stateless, ephemeral environment. Nothing is logged or stored after your agent receives its response.

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