Can I add items to my order after the shopper has been assigned?

Yes! As long as the order status is currently 'shopping', you can use the `update_order` tool to pass a JSON array with new product IDs and quantities. The Shopper's app will update dynamically with the new additions.

How can I find out the exact location of my delivery?

If the order has reached the 'delivering' status, you can invoke the `track_order` tool with your order ID. It will return the last known latitude/longitude of the courier along with the ETA (Estimated Time of Arrival) to your destination address.

Does this work across all LATAM countries where Cornershop operates?

Yes. The API uses global endpoints. When mapping stores using `list_stores`, you supply your local latitude and longitude to receive the stores available in your immediate geographic region (Chile, Mexico, Brazil, Colombia, Peru, etc).

Cornershop MCP Server for Google ADK 14 tools — connect in under 2 minutes

Name: Cornershop
Availability: InStock
Author: Vinkius

google.github.io/adk-docs/tools/mcp-tools

Built by Vinkius GDPR 14 Tools SDK

Google Agent Development Kit (ADK) is Google's framework for building production AI agents. Add Cornershop as an MCP tool provider through Vinkius and your ADK agents can call every tool with full schema introspection.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

from google.adk.agents import Agent
from google.adk.tools.mcp_tool import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import (
    StreamableHTTPConnectionParams,
)

# Your Vinkius token. get it at cloud.vinkius.com
mcp_tools = McpToolset(
    connection_params=StreamableHTTPConnectionParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    )
)

agent = Agent(
    model="gemini-2.5-pro",
    name="cornershop_agent",
    instruction=(
        "You help users interact with Cornershop "
        "using 14 available tools."
    ),
    tools=[mcp_tools],
)

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Cornershop MCP Server

Connect your Cornershop by Uber B2B account to any AI agent and manage your last-mile grocery delivery operations through natural conversation.

Google ADK natively supports Cornershop as an MCP tool provider. declare Vinkius Edge URL and the framework handles discovery, validation, and execution automatically. Combine 14 tools with Gemini's long-context reasoning for complex multi-tool workflows, with production-ready session management and evaluation built in.

What you can do

Store & Product Discovery — Search through connected retail partners (Jumbo, Lider, pharmacies), browse their aisles, and find specific SKUs with real-time pricing and availability
Order Creation — Construct shopping carts dynamically and place delivery orders directly through your AI agent
Live Tracking — Monitor the real-time status of your orders, from picking to delivery, including GPS tracking of the assigned Shopper
Order Modification — Add or remove items from the cart while the Shopper is still in the store, without opening the mobile app
Shopper Communication — Retrieve contact details for assigned Shoppers to resolve delivery issues instantly

The Cornershop MCP Server exposes 14 tools through the Vinkius. Connect it to Google ADK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Cornershop to Google ADK via MCP

Follow these steps to integrate the Cornershop MCP Server with Google ADK.

Install Google ADK

Run pip install google-adk

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Create the agent

Save the code above and integrate into your ADK workflow

Explore tools

The agent will discover 14 tools from Cornershop via MCP

Why Use Google ADK with the Cornershop MCP Server

Google ADK provides unique advantages when paired with Cornershop through the Model Context Protocol.

Google ADK natively supports MCP tool servers. declare a tool provider and the framework handles discovery, validation, and execution

Built on Gemini models, ADK provides long-context reasoning ideal for complex multi-tool workflows with Cornershop

Production-ready features like session management, evaluation, and deployment come built-in. not bolted on

Seamless integration with Google Cloud services means you can combine Cornershop tools with BigQuery, Vertex AI, and Cloud Functions

Cornershop + Google ADK Use Cases

Practical scenarios where Google ADK combined with the Cornershop MCP Server delivers measurable value.

Enterprise data agents: ADK agents query Cornershop and cross-reference results with internal databases for comprehensive analysis

Multi-modal workflows: combine Cornershop tool responses with Gemini's vision and language capabilities in a single agent

Automated compliance checks: schedule ADK agents to query Cornershop regularly and flag policy violations or configuration drift

Internal tool platforms: build self-service agent platforms where teams connect their own MCP servers including Cornershop

Cornershop MCP Tools for Google ADK (14)

These 14 tools become available when you connect Cornershop to Google ADK via MCP:

cancel_order

Note: Orders can only be cancelled without penalty if the shopper hasn't started picking. Cancel a pending order

create_order

Requires a JSON string defining the cart (product IDs, quantities) and delivery address details. Place a new delivery order

create_webhook

g., shopper_assigned, order_delivered). Create a new explicit webhook

get_order

Get full details of a specific order

get_product

Get details of a specific product

get_store

Get details of a specific store branch

list_orders

List your delivery orders

list_shoppers

Get information about the assigned Shopper

list_store_aisles

List categories and aisles of a store

list_stores

g. Jumbo, Lider, pharmacies). Can be geographically filtered by latitude and longitude. List available grocery stores and partners

list_webhooks

List configured order webhooks

search_products

Returns matching SKUs, names, current pricing, and availability. Search for specific groceries and products

track_order

Get real-time tracking for a delivery

update_order

Useful for last-minute replacements or additions. Update an active order (e.g. add/remove items)

Example Prompts for Cornershop in Google ADK

Ready-to-use prompts you can give your Google ADK agent to start working with Cornershop immediately.

"Search for Jumbo stores near latitude -33.4372 and longitude -70.6506 (Santiago Centro)."

"Where is the shopper for my order #CS-44919?"

"Place an order at Lider (ID: LDR-10) for 2 units of SKU 'Milk-Whole-1L' and deliver into the corporate office."

Troubleshooting Cornershop MCP Server with Google ADK

Common issues when connecting Cornershop to Google ADK through the Vinkius, and how to resolve them.

McpToolset not found

Update: pip install --upgrade google-adk

Cornershop + Google ADK FAQ

Common questions about integrating Cornershop MCP Server with Google ADK.

How does Google ADK connect to MCP servers?

Import the MCP toolset class and pass the server URL. ADK discovers and registers all tools automatically, making them available to your agent's tool-use loop.

Can ADK agents use multiple MCP servers?

Yes. Declare multiple MCP tool providers in your agent configuration. ADK merges all tool schemas and the agent can call tools from any server in a single turn.

Which Gemini models work best with MCP tools?

Gemini 2.0 Flash and Pro models both support function calling required for MCP tools. Flash is recommended for latency-sensitive use cases, Pro for complex reasoning.