How to Use the Normality Test Engine MCP in Pydantic AI

Q: How do I use Normality Test Engine with Pydantic AI?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your HTTP endpoint and pass it directly to the toolsets array in your Agent constructor.

Type-safe Jarque-Bera tests for your agent. Catch skewed data before it ruins your analysis with Pydantic AI.

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 Pydantic AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-validated statistics for Pydantic AI

The `test_normality` tool executes exact skewness and kurtosis calculations while your framework validates every output at runtime. If the engine returns a string instead of a float for the p-value, your agent fails loudly. You never pass corrupted math into downstream functions. You initialize your MCP Server connection with your endpoint and hand it to your agent. The framework ensures the numeric data array matches the exact schema before the request even leaves your machine. No silent failures. No hallucinated metrics.

Model-agnostic MCP Server execution

You swap underlying LLMs without rewriting your statistical logic. Because the MCP Server runs externally and connects via standard protocols, you can use Anthropic today and a local model tomorrow. The Jarque-Bera math remains identical. The framework parses the tool response and forces the language model to respect the deterministic output. The agent reads the exact skewness score and makes a routing decision based on hard logic, not probabilistic guessing.

Strict schema adherence for data arrays

Statistical tests crash if fed dirty data. Pydantic guarantees the inputs. Before the agent invokes the tool, it formats the raw data into a strictly typed array of floats. The engine receives clean input, runs the Jarque-Bera test, and returns a structured response. You rely on this strict contract to build autonomous pipelines that do not collapse when they encounter an unexpected null value.

Setup guide

Set up Normality Test Engine MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "normality-test-engine-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Normality Test Engine tools.",
)

result = await agent.run("List recent Normality Test Engine transactions")
print(result.output)

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 Pydantic AI

Install pydantic-ai-slim[mcp]. Initialize an MCPToolset with your HTTP endpoint and pass it directly to the toolsets array in your Agent constructor.

No. LLMs hallucinate math. The agent sends the numeric array to the external engine, which computes the exact statistics and returns them safely.

The framework throws a strict validation error immediately. It fails loudly, preventing your application from silently accepting corrupted statistical outputs.

Yes. The framework is model-agnostic. As long as the model supports tool calling, it can send arrays to the MCP Server and receive the calculated kurtosis.

You send specific numeric arrays to the endpoint. The server calculates the test statistics in ephemeral memory, returns the typed response, and immediately discards your raw floats.

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