How to Use the iFood MCP in Cursor

Q: Can Cursor use iFood tools to debug my code?

Absolutely. You can have the agent call getorderdetails to inspect why a specific order failed to dispatch, then adjust your code accordingly.

Build custom delivery logic in Cursor. Use live order data to write and test your own fulfillment automation code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect iFood MCP to Cursor

Create your Vinkius account to connect iFood to Cursor 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 iFood with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate dispatching in Cursor

Write scripts that trigger `assign_driver` based on your own internal logic. Cursor allows you to use live data from `get_orders` to decide which drivers get which routes. You are no longer guessing. The AI writes code that interacts with the real delivery network, meaning your automation handles production orders.

Sync catalog updates via Cursor

Pull your entire menu structure with `get_catalog` and let the AI generate bulk updates. Use `update_catalog_item` to push price changes directly to the store. This workflow removes the lag between price adjustments and store visibility. You code the logic, and the tools handle the API calls.

Manage store hours with Cursor

Use `get_business_hours` to audit your current store settings before writing automation scripts. If you need to handle holiday schedules, `update_business_hours` applies the changes programmatically. Your code controls the store's status. It ensures your operational hours are always consistent with your backend configuration.

Setup guide

Set up iFood MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the iFood MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent iFood transactions." If the MCP tools are loaded correctly, Cursor will call the iFood tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "ifood-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 iFood. 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 iFood 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 iFood MCP in Cursor

Create a .cursor/mcp.json file in your project root. Define the server path there so your agent can start calling tools immediately.

Absolutely. You can have the agent call `get_order_details` to inspect why a specific order failed to dispatch, then adjust your code accordingly.

Keys are handled by the server configuration. They are never exposed in your codebase and remain isolated from your repo history.

It gives the AI context about your live store environment. You get working code that interacts with real API responses rather than hardcoded stubs.

The server only reads and writes the specific order records you request. Your sensitive business logs never leave the secure transport channel.

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

Mastra AI sdk-typescript

Start using the iFood MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started