How to Use the InnoVint MCP in Google ADK

Q: How do I register the InnoVint MCP Server tools within my Google ADK setup?

Use pip install google-adk and create an McpToolset pointing to your Vinkius HTTP URL. Pass this toolset into the tools list of your LlmAgent to let Gemini search wine lots and check vessel capacities.

Run Gemini-powered Google ADK agents to manage cellar space, analyze wine chemistry, and track lots across your winery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect InnoVint MCP to Google ADK

Create your Vinkius account to connect InnoVint 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 InnoVint with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Track cellar operations using Google ADK and Gemini

Bring your winery data directly into your Google Cloud ecosystem. By linking the InnoVint MCP Server to your Google ADK pipeline, Gemini models use long-context reasoning to analyze years of cellar work. The agent calls `list_actions` to pull historical data and map it against current tank statuses. You initialize this by defining an `McpToolset` with your HTTP server parameters. When your agent runs, it calls `search_lots` to parse complex varietal compositions and match them with active vessel locations in your warehouse.

Cross-reference BigQuery datasets with physical vessel space

This MCP Server lets your agent connect physical cellar operations with your enterprise data warehouse. Your agent can query your database for market demand, then call `list_vessels` and `get_vessel` to check if you have the stainless steel tank capacity to handle a new block of Chardonnay. To keep your agent focused, use the tool name filter in the ADK setup. You can restrict the agent's access to only `list_vessels` and `get_lot` if you want to prevent it from viewing sensitive regulatory limits or additive histories.

Monitor wine chemistry trends over long aging cycles

Aging wine requires constant monitoring of sulfur dioxide and volatile acidity levels. Your agent can use `list_analyses` to fetch historical chemistry logs for any specific lot over several years. Gemini's massive token window handles these long logs easily, spotting trends that human cellar masters might miss. If the agent spots a drift in pH, it calls `list_additives` to check standard dosage rules and regulatory caps before recommending an adjustment. It can also query `list_wines` and `list_vintages` to compare the current batch with previous successful years.

Setup guide

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

Use `pip install google-adk` and create an `McpToolset` pointing to your Vinkius HTTP URL. Pass this toolset into the `tools` list of your `LlmAgent` to let Gemini search wine lots and check vessel capacities.

Yes, the ADK lets you pass an optional list of tool names to your toolset constructor. You can restrict your agent to only read-only tools like `get_lot` and `list_analyses` if you want to keep cellar history secure.

Gemini models use their massive token limits to digest years of cellar logs. The agent calls `list_actions` and `list_vessels` to pull entire historical records for a lot, mapping out every barrel transfer and lab analysis in one go.

Yes. You can configure your toolset to connect via standard input/output or streamable HTTP depending on where your Google Cloud agent environment is hosted.

Your tank fill levels, barrel locations, and vessel volumes queried via `get_vessel` are transmitted over encrypted TLS directly to your ADK agent. Vinkius runs this MCP Server in an ephemeral sandbox, meaning no physical cellar layout data or lot volumes are cached or stored on external 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