How to Use the iFood MCP in AutoGen

Let your AutoGen agents debate iFood logistics. Coordinate driver assignments and store updates through collaborative multi-agent discussion.

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 AutoGen

Create your Vinkius account to connect iFood to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate iFood order fulfillment in AutoGen

Set up a dispatcher agent and a store manager agent. They use `get_orders` to review volume and discuss whether to trigger `assign_driver` based on current capacity. This deliberation ensures you don't over-assign drivers during busy periods. Your agents reach a consensus before taking action.

Manage iFood store hours with AutoGen agents

Have your agents review store schedules using `get_business_hours`. If the data looks off, the agents debate the correct update and call `update_business_hours`. They verify the change by checking the tool response. You get an audit trail of why the schedule was modified.

Automated iFood catalog negotiation

Create agents that monitor pricing trends. One agent suggests a change via `update_catalog_item` while another validates it against your store goals. They negotiate the price point until they agree. This keeps your catalog competitive without you needing to intervene.

Setup guide

Set up iFood MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes iFood tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="iFood_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent iFood data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="iFood_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent iFood data")
    print(result.messages[-1].content)

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 AutoGen

You assign specific roles to agents, like logistics or menu management. They communicate and call tools like `assign_driver` or `get_catalog` to reach their goals.

They debate their proposed actions. If one agent wants to change a price and another disagrees, they reconcile the decision before calling `update_catalog_item`.

Yes. You provide the tool list to the group chat configuration. Every agent in the group has access to the same set of store management functions.

AutoGen logs the entire conversation history. You see the debate, the tool calls like `get_orders`, and the final consensus for every order.

The server uses ephemeral sessions. Sensitive order details are restricted to the agent conversation and are never persisted beyond the current task.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python