iFood MCP Server for LlamaIndex 11 tools — connect in under 2 minutes
LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add iFood as an MCP tool provider through Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI
async def main():
# Your Vinkius token. get it at cloud.vinkius.com
mcp_client = BasicMCPClient("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
mcp_tool_spec = McpToolSpec(client=mcp_client)
tools = await mcp_tool_spec.to_tool_list_async()
agent = FunctionAgent(
tools=tools,
llm=OpenAI(model="gpt-4o"),
system_prompt=(
"You are an assistant with access to iFood. "
"You have 11 tools available."
),
)
response = await agent.run(
"What tools are available in iFood?"
)
print(response)
asyncio.run(main())
* 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 iFood MCP Server
What you can do
Transform your iFood merchant operations with AI-powered automation. Your agents can:
LlamaIndex agents combine iFood tool responses with indexed documents for comprehensive, grounded answers. Connect 11 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.
- Monitor incoming orders in real-time with status tracking
- Accept and progress orders through preparation workflow
- Manage restaurant catalogs — update prices, availability, descriptions
- Review order details including customer info, items, and totals
- Configure operating hours for each day of the week
- Track delivery logistics and assign drivers to orders
- View store information and configuration across all locations
The iFood MCP Server exposes 11 tools through the Vinkius. Connect it to LlamaIndex 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 iFood to LlamaIndex via MCP
Follow these steps to integrate the iFood MCP Server with LlamaIndex.
Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token
Run the agent
Save to agent.py and run: python agent.py
Explore tools
The agent discovers 11 tools from iFood
Why Use LlamaIndex with the iFood MCP Server
LlamaIndex provides unique advantages when paired with iFood through the Model Context Protocol.
Data-first architecture: LlamaIndex agents combine iFood tool responses with indexed documents for comprehensive, grounded answers
Query pipeline framework lets you chain iFood tool calls with transformations, filters, and re-rankers in a typed pipeline
Multi-source reasoning: agents can query iFood, a vector store, and a SQL database in a single turn and synthesize results
Observability integrations show exactly what iFood tools were called, what data was returned, and how it influenced the final answer
iFood + LlamaIndex Use Cases
Practical scenarios where LlamaIndex combined with the iFood MCP Server delivers measurable value.
Hybrid search: combine iFood real-time data with embedded document indexes for answers that are both current and comprehensive
Data enrichment: query iFood to augment indexed data with live information before generating user-facing responses
Knowledge base agents: build agents that maintain and update knowledge bases by periodically querying iFood for fresh data
Analytical workflows: chain iFood queries with LlamaIndex's data connectors to build multi-source analytical reports
iFood MCP Tools for LlamaIndex (11)
These 11 tools become available when you connect iFood to LlamaIndex via MCP:
assign_driver
Requires order ID and driver ID. Use this to manage your own delivery fleet and coordinate order fulfillment. Assign a delivery driver to an iFood order
get_business_hours
Use this to review or verify the current schedule before making changes. Get operating hours for an iFood store
get_catalog
Use this to review menu structure, check item availability, or prepare updates to pricing or descriptions. Get the menu catalog for an iFood store
get_logistics
Use this to track order fulfillment and coordinate with delivery personnel. Get logistics/delivery information for an iFood order
get_order_details
Use this to review order contents before accepting or preparing. Get complete details of a specific iFood order
get_orders
Can filter by status: PENDING, ACCEPTED, PREPARING, READY, DISPATCHED, DELIVERED, CANCELLED. Returns order number, customer info, items, totals, and timestamps. Use this to monitor order flow and track pending orders. List orders for an iFood store
get_store_details
Use this to review store configuration before making updates. Get detailed information about a specific iFood store
get_stores
Returns store IDs, names, addresses, and operational status. Use this first to get store IDs needed for other operations like fetching orders or managing catalogs. List all stores associated with the iFood merchant account
update_business_hours
Requires a schedule object with open/close times for each day. Use this to change store hours, add weekend schedules, or set holiday closures. The schedule should be a JSON object with day keys (monday, tuesday, etc.) and arrays of {start: "HH:MM", end: "HH:MM"} objects. Update operating hours for an iFood store
update_catalog_item
Only pass the fields you want to change. Common use: update prices, toggle availability, or change descriptions. Requires store ID and item ID. Update a menu item in the iFood store catalog
update_order_status
Common workflow: PENDING -> ACCEPTED -> PREPARING -> READY -> DISPATCHED -> DELIVERED. Can also set to CANCELLED if needed. Use this to progress orders through the fulfillment pipeline. Update the status of an iFood order
Example Prompts for iFood in LlamaIndex
Ready-to-use prompts you can give your LlamaIndex agent to start working with iFood immediately.
"Show me all pending orders and accept them automatically"
"Update the price of 'Combo Burger Especial' to R$32.90 and mark it as unavailable until tomorrow"
"Change my store hours to open at 11am and close at 11pm every day this week"
Troubleshooting iFood MCP Server with LlamaIndex
Common issues when connecting iFood to LlamaIndex through the Vinkius, and how to resolve them.
BasicMCPClient not found
pip install llama-index-tools-mcpiFood + LlamaIndex FAQ
Common questions about integrating iFood MCP Server with LlamaIndex.
How does LlamaIndex connect to MCP servers?
Can I combine MCP tools with vector stores?
Does LlamaIndex support async MCP calls?
Connect iFood with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect iFood to LlamaIndex
Get your token, paste the configuration, and start using 11 tools in under 2 minutes. No API key management needed.