How to Use the Normality Test Engine MCP in Google ADK

Q: How do I restrict the agent to only this tool?

Use the toolnames argument when setting up your McpToolset. This forces the Gemini agent to only see and use the normality testing function.

Validate BigQuery datasets with exact Jarque-Bera tests using the Normality Test Engine for Google ADK.

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 Google ADK

Create your Vinkius account to connect Normality Test Engine to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery data validation via MCP Server

The `test_normality` tool evaluates your extracted BigQuery arrays for skewness and kurtosis. Gemini models handle massive context windows, but they still fail at raw arithmetic on thousands of floats. You need a dedicated engine to run the actual Jarque-Bera math. You pass the `McpToolset` directly to your `LlmAgent`. The agent pulls the numeric data from Google Cloud, feeds it to the tool, and gets back an exact p-value. This prevents your enterprise pipelines from running parametric models on skewed distributions.

Filtered tool access for Gemini agents

You dictate exactly what your agent can do by restricting exposed tools. Using the `tool_names` filter in your Google ADK setup, you lock the agent down to just the normality check. It cannot wander off and execute unrelated operations. The agent reads the numeric array, triggers the computation, and uses the result to decide its next step. If the data is normal, it proceeds with standard Vertex AI modeling. If it fails, it flags the dataset for manual review.

Deterministic math over HTTP or Stdio

Enterprise deployments require flexible infrastructure. You connect the MCP Server using either HTTP or Stdio transports depending on your Google Cloud architecture. The agent framework handles the communication layer automatically. You stop relying on LLMs to guess statistical validity. The engine calculates the exact metrics locally and returns them to Gemini. You get hard numbers you can actually trust in a production environment.

Setup guide

Set up Normality Test Engine MCP in Google ADK

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Normality Test Engine tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Normality Test Engine_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Normality Test Engine tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Install google-adk via pip. Create an McpToolset using StreamableHttpServerParameters and pass it to your LlmAgent initialization.

Language models cannot calculate kurtosis reliably. This server provides a deterministic execution environment to run exact statistical math outside the LLM.

Yes. Your agent queries BigQuery, formats the output as a numeric array, and sends it to the MCP Server. The engine returns the test statistics so your agent can route the workflow.

Use the tool_names argument when setting up your McpToolset. This forces the Gemini agent to only see and use the normality testing function.

The server processes your numeric arrays in memory to calculate the Jarque-Bera test. It never logs the raw floats or writes them to disk, ensuring your proprietary enterprise metrics remain private.

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