How to Use the iFood MCP in LlamaIndex

Q: How does iFood data integrate with LlamaIndex?

You pull data via tools like getcatalog or getorders and pass them into your document indexers. This creates a searchable version of your store activity.

Q: Can LlamaIndex query my iFood order history?

It can. By indexing the output of getorders, you enable natural language queries against your completed and pending transactions.

Q: Is iFood menu data updated in my index?

You refresh the index by calling getcatalog periodically. This ensures your agent has the latest item availability and pricing for its queries.

Q: How do I filter which tools LlamaIndex uses?

Use the allowedtools parameter when initializing your tool spec. This restricts the agent to specific operations like getlogistics or updatebusinesshours.

Index your iFood operations in LlamaIndex. Turn live order and catalog data into a searchable knowledge base for your agents.

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 LlamaIndex

Create your Vinkius account to connect iFood to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index iFood catalog data in LlamaIndex

Turn your menu data into a vector index. By calling `get_catalog`, you feed structured item data into your knowledge base for semantic retrieval. Your agent answers questions about inventory or pricing by querying the index. It stops guessing and starts using actual menu state.

Search past iFood orders with LlamaIndex

Store your order history in a searchable format. Use `get_orders` to populate your index with recent transaction data and customer details. This allows your agent to look up historical order trends. You gain insight into store performance without digging through raw logs.

Ground your MCP Server responses in live data

Use `get_store_details` to keep your agent informed about current store status. LlamaIndex indexes these details so your agent stays grounded in reality. It prevents hallucinations by forcing the agent to consult the indexed API state. Your decisions are backed by the most recent store configuration.

Setup guide

Set up iFood MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all iFood MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to iFood tools.",
)
response = await agent.run("List recent iFood data")

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 LlamaIndex

You pull data via tools like `get_catalog` or `get_orders` and pass them into your document indexers. This creates a searchable version of your store activity.

It can. By indexing the output of `get_orders`, you enable natural language queries against your completed and pending transactions.

You refresh the index by calling `get_catalog` periodically. This ensures your agent has the latest item availability and pricing for its queries.

Use the allowed_tools parameter when initializing your tool spec. This restricts the agent to specific operations like `get_logistics` or `update_business_hours`.

Your order data is stored in your local vector index. The server only touches the specific order IDs and customer info you request during execution.

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