How to Use the GrabFood Partner MCP in AutoGen

Q: Can AutoGen agents coordinate GrabFood Partner marketing campaigns?

Yes. An analyst agent can review past campaigns using listcampaigns, propose a new budget, and have the manager agent execute createcampaign once they agree on the parameters.

Q: What happens if an order needs to be cancelled?

The team first runs checkordercancelable to see if it is safe. If the cancellation window is still open, the manager agent executes cancelorder with a logged reason.

Deploy a multi-agent AutoGen team to debate and coordinate your GrabFood Partner store operations in real-time via our 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 GrabFood Partner MCP to AutoGen

Create your Vinkius account to connect GrabFood Partner 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 GrabFood Partner with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Negotiate order acceptance through agent debate

The `accept_order` tool is executed only after your AutoGen agents reach a consensus on kitchen capacity. A dedicated kitchen agent monitors prep times while a delivery agent tracks incoming orders, debating whether to accept or reject. If the kitchen agent flags a backup, the team may decide to call `pause_store` instead. This consensus-driven workflow prevents your restaurant from accepting orders it cannot fulfill on time.

Execute safe menu updates via MCP Server tools

The `batch_update_menu` tool allows your agent team to modify specific menu items after verifying stock levels. A stock-auditor agent identifies low ingredients and proposes an update, which the manager agent approves. Once approved, the tool executes the changes on GrabFood. This multi-agent verification process eliminates human error and keeps your online menu perfectly aligned with your physical pantry.

Coordinate order readiness and driver dispatch

The `mark_order_ready` tool notifies GrabFood that the food is packed and ready for collection. Your AutoGen coordinator agent invokes this tool only after the kitchen agent confirms preparation is complete. If a delay occurs, a separate agent can proactively trigger `update_ready_time` to push back the dispatch window. This tight coordination keeps delivery drivers happy and preserves your food quality.

Setup guide

Set up GrabFood Partner 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 GrabFood Partner 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="GrabFood Partner_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent GrabFood Partner 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="GrabFood Partner_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent GrabFood Partner 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 GrabFood Partner. 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 GrabFood Partner 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 GrabFood Partner MCP in AutoGen

Use the autogen-ext package to import MCP tools. Pass your Vinkius connection parameters to StreamableHttpServerParams, and supply the resulting tool list to your AssistantAgent.

Yes. An analyst agent can review past campaigns using `list_campaigns`, propose a new budget, and have the manager agent execute `create_campaign` once they agree on the parameters.

They use conversational consensus. If one agent wants to call `pause_store` due to a rush, but another sees active orders via `list_orders`, they debate the operational impact before executing the API call.

The team first runs `check_order_cancelable` to see if it is safe. If the cancellation window is still open, the manager agent executes `cancel_order` with a logged reason.

Absolutely. All communication between your AutoGen agents and the MCP Server is encrypted in transit. Your specific order details, campaign budgets, and menu data never leave your secure client execution environment.

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