How to Use the Arize AI MCP in Google ADK

Q: How do I configure Arize AI with Google ADK?

Install the google-adk package and initialize an McpToolset using your Vinkius HTTP URL. Pass this toolset to your LlmAgent under the tools parameter to expose the endpoints.

Q: Can Google ADK run Arize AI evaluations?

Your agent can execute the runeval tool to start custom LLM checks. You can restrict which checks are available by using the toolnames filter in your setup.

Q: How does Google ADK access my Arize AI metrics?

The agent calls getmetrics to fetch observability data for specific models. It can then use its long context window to analyze trends across thousands of data points at once.

Q: Can I push Vertex AI logs to Arize using this?

Yes, you can use the ingestlog tool to send raw telemetry. The agent formats your cloud logs into the required payload structure and pushes them to the platform.

Equip Google ADK with the Arize AI MCP Server to feed ML observability metrics directly into Gemini's massive context window.

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

Analyze Telemetry with Google ADK

The `get_metrics` and `list_models` tools pull observability data for tracked LLMs right into your Gemini agent using this MCP tool. Those massive 1M+ token context windows swallow entire historical performance reports in one gulp for deep reasoning. Enterprise setups usually split data across different stages. Calling `list_environments` lets the agent separate production inferences from Vertex AI training runs before analyzing the drift.

Trigger Evaluations from Gemini

Executing `run_eval` tells the agent to kick off automated checks for toxicity or hallucination. You can pipe the results straight into BigQuery for long-term storage and compliance reporting. To check what ran previously, the agent uses `list_evals`. It grabs the history of automated evaluation runs and cross-references them against your baseline data.

Manage Workspaces via MCP Server

The `list_spaces` tool reveals all accessible workspaces within the Arize platform. Your Gemini agent uses this to navigate between different models and telemetry datasets without hardcoded IDs. When you need to grab specific test data, `list_datasets` and `get_dataset` pull the exact evaluation records. The agent reads the static dataset and compares it against live logs ingested via `ingest_log`.

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 `google-adk` package and initialize an `McpToolset` using your Vinkius HTTP URL. Pass this toolset to your `LlmAgent` under the `tools` parameter to expose the endpoints.

Your agent can execute the `run_eval` tool to start custom LLM checks. You can restrict which checks are available by using the `tool_names` filter in your setup.

The agent calls `get_metrics` to fetch observability data for specific models. It can then use its long context window to analyze trends across thousands of data points at once.

Yes, you can use the `ingest_log` tool to send raw telemetry. The agent formats your cloud logs into the required payload structure and pushes them to the platform.

Your ML features and PII filtering logs pass through a zero-trust MCP tunnel using a single endpoint token. The ephemeral sandbox guarantees that your sensitive model inputs are completely isolated from other cloud workloads.

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