How to Use the Cornershop MCP in Mastra AI

Q: How do I handle out-of-stock items using Cornershop and Mastra AI?

You set up a conditional workflow. If getproduct shows zero availability, your Mastra AI agent calls searchproducts for substitutes and updates the cart using updateorder automatically.

Q: Can Mastra AI retry failed Cornershop orders automatically?

Yes, Mastra's retry engine intercepts failures during createorder. It retries the purchase with exponential backoff before escalating the failure or trying an alternative store branch.

Q: How do webhooks connect Cornershop events to Mastra AI workflows?

You run createwebhook to register your agent's endpoint. When a grocery status changes, the webhook triggers a Mastra AI workflow that runs trackorder to update your internal database.

Build resilient grocery delivery workflows with Mastra AI and the Cornershop MCP Server.

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 Mastra AI

Create your Vinkius account to connect Cornershop to Mastra AI 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build resilient grocery workflows with Mastra AI

Handling out-of-stock items during grocery runs requires dynamic tools like `search_products` and `get_product`. When you register these tools as Mastra AI agent actions via this MCP Server, you can build conditional logic that automatically finds replacements when a preferred item isn't on the shelf. If a specific brand of milk is missing, your Mastra AI workflow triggers `update_order` with an alternative. Mastra's built-in step execution ensures this replacement happens before the shopper checks out at the register.

Automated order recovery and retries

Recovering from failed checkouts is automated when your Mastra AI workflows run `create_order` with built-in retry logic. When your agent calls this tool, Mastra handles transient API failures with automatic backoffs, retrying the checkout process until the Uber backend confirms receipt. If the checkout fails permanently, your Mastra AI workflow branches to `list_stores` to find alternative branches. It then runs `list_store_aisles` to rebuild the cart and attempt a fresh purchase without manual intervention.

Event-driven shopper tracking

Listening for real-time order updates is easy when you configure `create_webhook` inside your Mastra AI workflows. This MCP Server lets your Mastra agent listen for status changes like shopper assignments or delivery arrivals. Once a webhook triggers, your Mastra AI workflow calls `list_shoppers` to pull driver details. It can then run `track_order` to coordinate drop-offs and notify your internal systems exactly when the groceries arrive.

Setup guide

Set up Cornershop MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Cornershop tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "cornershop-mcp-client",
  servers: {
    "cornershop-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Cornershop Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Cornershop tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Cornershop transactions"
);
console.log(result.text);

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 Mastra AI

You set up a conditional workflow. If `get_product` shows zero availability, your Mastra AI agent calls `search_products` for substitutes and updates the cart using `update_order` automatically.

Yes, Mastra's retry engine intercepts failures during `create_order`. It retries the purchase with exponential backoff before escalating the failure or trying an alternative store branch.

You run `create_webhook` to register your agent's endpoint. When a grocery status changes, the webhook triggers a Mastra AI workflow that runs `track_order` to update your internal database.

Yes, your Mastra AI agent can pass latitude and longitude to `list_stores`. This filters available LatAm retailers down to the exact delivery radius of your target address.

Order IDs and driver details are processed locally within our ephemeral sandbox. No transaction history or shopper contact info is stored on our servers, keeping your delivery logs isolated and secure.

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