How to Use the Outlier Detection Engine MCP in Google ADK

Clean your BigQuery datasets using Outlier Detection Engine directly within your Google ADK agent loops.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Outlier Detection Engine MCP to Google ADK

Create your Vinkius account to connect Outlier Detection Engine to Google ADK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Outlier Detection Engine with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Clean BigQuery Data Before Gemini Reasoning

Gemini models have massive context windows, but feeding them noisy data wastes tokens. Use the `detect_outliers` tool via your Google ADK setup to strip out statistical noise before passing datasets to your model using this MCP Server. This engine runs IQR and Z-Score calculations locally on your data. Your agent gets a clean, validated list of anomalies, keeping your 1M-token context window focused on actual analysis.

Enterprise-Grade Google ADK Toolsets

Wrap the server in an MCP toolset using the HTTP transport. You can restrict access to the `detect_outliers` tool by passing a tool_names filter directly to your LlmAgent configuration. This gives you granular control over what your enterprise agents can execute. Your Google Cloud pipelines stay secure while your models gain deterministic mathematical capabilities.

Deterministic Math on Vertex AI

Vertex AI models are great at reasoning but terrible at mental math. Instead of letting Gemini guess which rows look weird, let it call the `detect_outliers` tool to get mathematically proven outliers. The tool returns precise indices based on standard statistical formulas. Your agent can then safely drop these rows from your Vertex AI training runs.

Setup guide

Set up Outlier Detection 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 Outlier Detection 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="Outlier Detection Engine_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Outlier Detection 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 Outlier Detection 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 Outlier Detection Engine MCP in Google ADK

Your Google ADK agent pulls numeric data from BigQuery, feeds it directly to the `detect_outliers` tool, and receives the anomalous row indices. You can then write a clean dataset back to BigQuery without manual sorting.

Yes. You can configure your Google ADK agent's system instructions to only allow the IQR method when calling the `detect_outliers` tool. This ensures the agent doesn't try to use Z-Score on highly skewed, non-normal datasets.

An MCP Server provides a standardized, language-agnostic interface that runs in a secure sandbox. This prevents your Google ADK agents from executing unsafe, arbitrary python code just to calculate basic statistical boundaries.

Use the StreamableHttpServerParameters transport. It allows your Google Cloud hosted agents to communicate with the hosted server over a secure, authenticated HTTP connection with minimal latency.

Absolutely. The server processes your raw numbers inside an ephemeral, zero-trust sandbox. No data is stored or logged, keeping your sensitive enterprise metrics completely isolated from public clouds.

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