How to Use the Cornershop MCP in Google ADK

Q: Can I use Gemini's long context in Google ADK to analyze Cornershop store inventories?

Yes, you can dump entire product lists from liststoreaisles into Gemini's million-token window. The Google ADK agent easily parses thousands of grocery items without running out of memory.

Q: Can Google ADK filter Cornershop store branches geographically using the MCP Server?

Yes, your agent uses liststores with latitude and longitude arguments to target specific neighborhoods. This prevents your enterprise system from trying to order groceries from a store branch that is too far away.

Q: Is there a way to update an order after it has been placed?

Your agent can call updateorder to swap out items or add last-minute groceries. This tool is active until the shopper finishes picking, letting your system adapt to real-time inventory shifts.

Connect the Google ADK to Cornershop to automate enterprise grocery logistics and inventory analysis with Gemini long-context models.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cornershop MCP to Google ADK

Create your Vinkius account to connect Cornershop 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 Cornershop with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery-Driven Inventory Search

This MCP Server bridges Cornershop's real-time inventory tools directly with your Google ADK pipelines. Your agent calls `search_products` to pull current pricing and availability, matching the results against historical sales data stored in BigQuery. Gemini's massive context window lets you feed thousands of product lines returned by `list_store_aisles` directly into the model. The agent analyzes entire store layouts in one turn to optimize grocery restocking schedules.

Enterprise Logistics via Google ADK

This integration uses the MCP Server to let your Google ADK agent manage physical deliveries across multiple Latin American store branches. The agent runs `list_stores` with geographical coordinates to find the nearest partner branch, then queries `get_store` for operational hours. By combining Google Cloud's location data with these tools, your agent routes orders efficiently. Once the store is selected, the agent executes `create_order` to dispatch a shopper to that specific branch.

Automated Delivery Tracking

This system automates delivery monitoring by feeding live tracker data from the MCP Server into your Google Cloud operations center. Your agent uses `track_order` to pull real-time coordinates and updates your internal logistics database instantly. If a delay occurs, the agent calls `get_order` to inspect the cart status and cross-references it with BigQuery delivery logs. This ensures your enterprise dashboard always has an accurate picture of active grocery runs.

Setup guide

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

Yes, you can dump entire product lists from `list_store_aisles` into Gemini's million-token window. The Google ADK agent easily parses thousands of grocery items without running out of memory.

You configure your Google ADK agent to write the JSON payload returned by `get_order` directly to a BigQuery table. This lets you run SQL queries on your Latin American grocery spend over time.

Yes, your agent uses `list_stores` with latitude and longitude arguments to target specific neighborhoods. This prevents your enterprise system from trying to order groceries from a store branch that is too far away.

Your agent can call `update_order` to swap out items or add last-minute groceries. This tool is active until the shopper finishes picking, letting your system adapt to real-time inventory shifts.

Vinkius handles the underlying authentication tokens, passing only structured shopper names and coordinates to your Google Cloud environment. No persistent logs of these delivery details are saved on the proxy, maintaining strict enterprise data isolation.

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