How to Use the eCellar MCP in Google ADK

Q: How do I connect the eCellar MCP Server to Google ADK?

Install the google-adk package. Initialize an McpToolset with your server URL and pass it to your LlmAgent in the tools array.

Q: Can I restrict which eCellar tools my Google ADK agent sees?

You can use the toolnames filter during initialization. This lets you expose reservation data to a front-desk agent while hiding order histories.

Q: Does the eCellar MCP Server work with Gemini's long context?

Yes. You can dump thousands of records from listorders straight into the prompt. Gemini processes the massive payload without dropping details.

Feed eCellar DTC data directly into Google ADK to power enterprise agents with massive context windows and BigQuery integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect eCellar MCP to Google ADK

Create your Vinkius account to connect eCellar 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 eCellar with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze buyer behavior with Google ADK

The `search_customers` and `get_customer` tools pull lifetime spend and visit history directly into Gemini's massive context window. Your agent cross-references this CRM data with your existing BigQuery datasets to spot buying trends. You stop guessing about who buys your premium allocations and start acting on hard data. Tracking subscription revenue relies on the `list_clubs` and `list_club_members` endpoints. You pass the `McpToolset` to your `LlmAgent` and restrict access using the `tool_names` filter. This keeps your agent focused strictly on club metrics without getting distracted by unrelated inventory data.

Manage multi-location stock

Your agent queries the `list_inventory` tool to audit stock across different tasting rooms and warehouses. When discrepancies pop up, it hits `get_order` and `list_orders` to trace fulfillment status and payment records. You get immediate clarity on where your bottles are and who bought them. Google Cloud infrastructure handles the heavy lifting while the MCP server feeds it raw operational data. The integration runs over standard HTTP transports. Your supply chain decisions are now backed by real-time DTC metrics.

Organize tasting room schedules

The `list_reservations` tool pulls daily booking schedules so your agent can forecast tasting room traffic. It pairs this data with `list_products` and `get_product` to calculate exactly how many cases of each wine you need to pull from the cellar. Setting this up takes minutes. You install the `google-adk` package and initialize a `StreamableHttpServerParameters` object. The agent automatically knows how to filter reservations by date and match them to your ecommerce product catalog.

Setup guide

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

Install the `google-adk` package. Initialize an `McpToolset` with your server URL and pass it to your `LlmAgent` in the tools array.

You can use the `tool_names` filter during initialization. This lets you expose reservation data to a front-desk agent while hiding order histories.

Yes. You can dump thousands of records from `list_orders` straight into the prompt. Gemini processes the massive payload without dropping details.

Your agent pulls raw JSON from the server and can immediately format it for Vertex AI or BigQuery ingestion. The framework handles the data routing.

The server transmits club tier assignments and billing status over encrypted channels. Authentication requires a single endpoint token, and the ephemeral execution environment guarantees no subscription data leaks into external training sets.

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