How to Use the Arize AI MCP in Google ADK

Q: How do I set up Arize AI inside Google ADK?

Install the ADK package and initialize McpToolset with your Vinkius HTTP URL. Pass this toolset directly to your LlmAgent to expose all six MCP tools.

Q: Can Google ADK query raw ML spans from Arize AI?

Yes, the agent uses listspans to fetch execution traces. This allows Gemini to analyze latency and trace errors across your entire production setup.

Q: How does the MCP Server help with BigQuery data pipelines?

Your agent can pull project lists using listprojects and match them with BigQuery tables. This lets you run drift analysis on massive datasets directly from your agent.

Q: Can I restrict which tools the agent can access?

Yes, use the toolnames filter in your McpToolset configuration. This lets you limit the agent to read-only tools like listexperiments if you want to prevent dataset creation.

Connect Google ADK agents to your production telemetry to monitor Gemini model performance and track live spans.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arize AI MCP to Google ADK

Create your Vinkius account to connect Arize AI 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 Arize AI with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect Vertex AI models to this MCP Server

The `get_model` tool pulls performance metrics directly into your Gemini reasoning loop. Your agent checks these live stats to decide if it needs to route queries to a fine-tuned fallback model. This integration keeps your Google Cloud pipelines self-correcting. You don't have to write custom cloud functions just to monitor your model's prediction quality.

Google ADK automated dataset curation

The `create_dataset` tool exports production inputs directly from your agent's memory into your evaluation suites. This helps you build regression tests using actual user interactions. To prevent duplicate data entry, your agent queries `list_datasets` to verify existing suites before creating new ones. This structure keeps your testing environments clean.

Debug latency spikes across Google Cloud

The `list_spans` tool retrieves raw execution traces through the MCP connection. Your Gemini agent parses these spans to locate bottlenecks in external API calls or database queries. Combining this with `list_projects` lets the agent isolate issues within specific workspaces. You get instant diagnostics without digging through Google Cloud logging consoles.

Setup guide

Set up Arize AI 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 Arize AI 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="Arize AI_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Arize AI 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 Arize AI. 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 Arize AI 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 Arize AI MCP in Google ADK

Install the ADK package and initialize `McpToolset` with your Vinkius HTTP URL. Pass this toolset directly to your `LlmAgent` to expose all six MCP tools.

Yes, the agent uses `list_spans` to fetch execution traces. This allows Gemini to analyze latency and trace errors across your entire production setup.

Your agent can pull project lists using `list_projects` and match them with BigQuery tables. This lets you run drift analysis on massive datasets directly from your agent.

Yes, use the `tool_names` filter in your `McpToolset` configuration. This lets you limit the agent to read-only tools like `list_experiments` if you want to prevent dataset creation.

Absolutely, all API tokens and telemetry payloads are handled via ephemeral V8 isolates. Your ML datasets and span details are never persisted on Vinkius servers.

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