How to Use the Confusion Matrix Engine MCP in Google ADK

Q: How do I configure Confusion Matrix Engine within Google ADK?

Initialize an McpToolset pointing to the Vinkius HTTP endpoint for this MCP Server. Pass this toolset into your LlmAgent tools array to expose the matrix calculation tools to Gemini.

Q: Can I restrict Google ADK to only use Confusion Matrix Engine tools?

Yes. Use the toolnames filter when setting up your McpToolset to only allow the calculateconfusionmatrix tool, blocking any other operations.

Score BigQuery classification models using Google ADK and Gemini long-context reasoning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Confusion Matrix Engine MCP to Google ADK

Create your Vinkius account to connect Confusion Matrix 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 Confusion Matrix Engine with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Score BigQuery data with Google ADK

Enterprise classification pipelines often leave predictions sitting in BigQuery tables. By linking this MCP Server, your Gemini agent can pull those predictions and feed them straight into `calculate_confusion_matrix`. You get instant, deterministic evaluation metrics. This setup bypasses the need to write complex SQL window functions or export data to external notebooks.

High-token context window evaluations

Gemini models handle massive contexts, meaning you can pass thousands of classification data points at once. This tool takes advantage of that capacity by letting your agent process huge arrays of labels in a single pass. The `calculate_confusion_matrix` tool processes them without breaking a sweat. Instead of batching your evaluations into tiny chunks, you can feed entire test sets directly.

Secure MCP Server controls for cloud agents

Security in Google Cloud environments requires tight control over what your agents can execute. This MCP Server lets you use the `tool_names` filter in Google ADK to expose only the specific calculation tools you need. By limiting the scope, you ensure your agent only touches `calculate_confusion_matrix` and nothing else. This minimizes the attack surface of your cloud-deployed agent while still giving it the math capabilities it needs.

Setup guide

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

Initialize an `McpToolset` pointing to the Vinkius HTTP endpoint for this MCP Server. Pass this toolset into your `LlmAgent` tools array to expose the matrix calculation tools to Gemini.

Yes. Use the `tool_names` filter when setting up your `McpToolset` to only allow the `calculate_confusion_matrix` tool, blocking any other operations.

Yes. Your agent can read prediction rows from BigQuery, format them into lists, and pass them directly to the `calculate_confusion_matrix` tool.

The tool returns the full matrix alongside True Positives, False Positives, Precision, Recall, F1-Score, and Accuracy. It covers everything needed to evaluate a standard classifier.

Your arrays of actual and predicted labels are sent over an encrypted HTTPS connection to a zero-trust, isolated runtime. They are wiped from memory the millisecond the mathematical response is generated.

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