How to Use the K-Fold Split Engine MCP in Google ADK

Q: How do I limit Google ADK to only use the K-Fold Split Engine tool?

Use the toolnames filter when initializing your McpToolset. Pass only calculatekfold to ensure your Gemini agent cannot access other tools on that server.

Partition BigQuery datasets for Vertex AI pipelines using the K-Fold Split Engine with 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 K-Fold Split Engine MCP to Google ADK

Create your Vinkius account to connect K-Fold Split 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 K-Fold Split Engine with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery Partitioning with Google ADK

Pull your training data from BigQuery and use `calculate_kfold` to divide your tables into clean validation sets for your Google ADK agent. Since Google ADK supports deep enterprise integrations, you can feed these indices directly into Vertex AI training jobs. This MCP server keeps your entire Google ADK machine learning pipeline inside your secure cloud environment.

Long-Context Evaluation via MCP Server

Offload heavy index calculations to `calculate_kfold` so Gemini can analyze split distributions within its Google ADK long-context window. By keeping the math external, this setup avoids memory bottlenecks in Google ADK. Your agent focuses entirely on validation bias instead of processing raw arrays.

Granular Tool Control for Enterprise Agents

Restrict your Google ADK cloud agents to specific validation tasks by exposing only `calculate_kfold` in your agent configuration. With this focused setup, you secure your automated Google ADK workflows. This MCP utility secures your automated Google ADK workflows so cloud agents can generate cross-validation splits for your data science team without gaining access to other system utilities.

Setup guide

Set up K-Fold Split 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 K-Fold Split 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="K-Fold Split Engine_agent",
    model="gemini-2.0-flash",
    instruction="You have access to K-Fold Split 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 Native V8. 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 K-Fold Split 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 K-Fold Split Engine MCP in Google ADK

Yes. Your Google ADK agent can fetch row counts from BigQuery, pass them to `calculate_kfold`, and use the returned index arrays to partition your tables for Vertex AI training.

Use the tool_names filter when initializing your McpToolset. Pass only `calculate_kfold` to ensure your Gemini agent cannot access other tools on that server.

Yes. You can connect this MCP toolset using either Stdio or Streamable HTTP transports depending on where your Google ADK agent is hosted.

Gemini can digest thousands of generated indices returned by `calculate_kfold` at once. This lets the agent analyze the entire split structure for potential class distribution imbalances.

The MCP server only receives numerical parameters like row counts and fold configurations. It generates integer index lists in a secure sandbox, ensuring no raw tabular data or text strings ever leave your Google Cloud project.

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