How to Use the H2O.ai MCP in Google ADK

Q: How do I link H2O.ai tools to a Google ADK agent?

You define an McpToolset pointing to your server URL and pass it into the LlmAgent configuration. The tools become available to your agent immediately.

Q: Can Google ADK list frames from H2O.ai?

Yes. Using listframes allows your agent to see all available data structures. It then uses getframe to inspect specific contents as needed.

Q: How do I filter which H2O.ai tools Google ADK uses?

You can use the toolnames filter in your McpToolset definition. This restricts the agent to only the specific operations you want to permit.

Connect H2O.ai to your Google ADK agents. Automate model oversight and cluster audits directly within your GCP environment.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect H2O.ai MCP to Google ADK

Create your Vinkius account to connect H2O.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 H2O.ai with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit model performance with Google ADK

Your agent calls `list_models` to inventory your current model library. It surfaces performance metrics so you can verify if a model is ready for inference. Detailed inspection happens via `get_model`. This gives your agent the specific versioning data it needs to switch between production and staging models.

Manage training lifecycles via Google ADK

The `list_jobs` tool allows your agent to watch training progress in real-time. It identifies failures as soon as they hit the API. When a job completes, the agent can trigger downstream tasks based on the metadata. This keeps your model pipeline running without a human in the loop.

Expose H2O.ai cluster status to Google ADK

The `cloud_status` tool gives your agent visibility into cluster health. It allows your code to pause tasks if the underlying infrastructure is under heavy load. By integrating this directly into your agent, you ensure your resource usage matches your current capacity. It keeps your GCP workflows efficient.

Setup guide

Set up H2O.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 H2O.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="H2O.ai_agent",
    model="gemini-2.0-flash",
    instruction="You have access to H2O.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 H2O.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 H2O.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 H2O.ai MCP in Google ADK

You define an `McpToolset` pointing to your server URL and pass it into the `LlmAgent` configuration. The tools become available to your agent immediately.

Yes. Using `list_frames` allows your agent to see all available data structures. It then uses `get_frame` to inspect specific contents as needed.

The tools operate on standard HTTP requests. Response times depend on your cluster load, but the MCP Server is built to minimize overhead during status checks.

You can use the `tool_names` filter in your `McpToolset` definition. This restricts the agent to only the specific operations you want to permit.

The server uses token-based authentication to guard all requests. It restricts access to model metadata and job logs, ensuring only authorized agents can interact with your cluster environment.

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