How to Use the Cornershop MCP in OpenAI Agents SDK

Q: Can I trace Cornershop API latency using the OpenAI Agents SDK dashboard?

Yes, every tool call like searchproducts or getstore shows up directly in your OpenAI run traces. You can see the exact execution time and token cost for each grocery search or store lookup.

Q: How does the OpenAI Agents SDK manage shopper updates from the Cornershop MCP Server?

Your agent runs listshoppers to fetch the picker's current status and name. You can configure a specialized tracking agent to handle this data, keeping the main ordering agent focused on cart construction.

Q: What happens if I need to cancel a grocery delivery?

Your agent invokes cancelorder immediately. The tool checks if the picker has started their run, ensuring you avoid cancellation penalties when managing automated restocks.

Get your OpenAI Agents SDK system ordering, tracking, and managing LatAm grocery deliveries through Cornershop without custom API glue.

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 OpenAI Agents SDK

Create your Vinkius account to connect Cornershop to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guardrail-Protected Grocery Ordering

This MCP Server exposes direct grocery procurement endpoints to your OpenAI Agents SDK setup. You pass the schema to your agent, and it uses `create_order` to send a JSON payload with delivery coordinates and product IDs directly to Cornershop. OpenAI's built-in guardrails step in before the order fires, validating the cart structure against your parameters. If a shopper makes a mistake, your supervisor agent intercepts the payload, preventing accidental duplicate orders from hitting your corporate card.

Multi-Agent Delivery Tracking

This MCP Server coordinates real-time delivery status updates across your specialized OpenAI agent network. When a delivery is active, one agent uses `track_order` to pull the latest coordinates, while another agent runs `list_shoppers` to check who is picking the items. You can easily pass the context from the tracking agent to a customer-facing agent using the SDK's native handoffs. If the shopper runs into issues, the agent triggers `update_order` to swap out an out-of-stock item before the picker leaves the aisle.

Automated Webhook MCP Server Configuration

This tool configuration lets your OpenAI Agents SDK monitor order updates passively rather than spamming the API with search requests. Your agent registers endpoints with `create_webhook` and monitors active webhooks using `list_webhooks`. By offloading active polling, your system cuts token usage on the OpenAI dashboard. The agent only spins up to process changes when Cornershop pushes a state change, like when a shopper is assigned.

Setup guide

Set up Cornershop MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Cornershop tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Cornershop tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Cornershop tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Cornershop Agent",
            instructions="You have access to Cornershop tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You configure OpenAI's built-in guardrails to inspect the JSON payload before `create_order` executes. This stops the agent from sending malformed address schemas or invalid product IDs to the Cornershop API.

Yes, every tool call like `search_products` or `get_store` shows up directly in your OpenAI run traces. You can see the exact execution time and token cost for each grocery search or store lookup.

Your agent runs `list_shoppers` to fetch the picker's current status and name. You can configure a specialized tracking agent to handle this data, keeping the main ordering agent focused on cart construction.

Your agent invokes `cancel_order` immediately. The tool checks if the picker has started their run, ensuring you avoid cancellation penalties when managing automated restocks.

All grocery delivery addresses and order history remain inside Vinkius's ephemeral sandboxed environment. Your OpenAI client receives the structured response over an encrypted SSE connection, ensuring no raw location data is cached or exposed.

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