How to Use the Ele.me Open Platform / 饿了么 MCP in AutoGen

Q: How do I get my AutoGen agents to use the Ele.me Open Platform / 饿了么 tools?

After installing the autogen-extmcp package, call mcpservertools with your Vinkius URL. This MCP function returns a list of tools you can pass directly to your AssistantAgent—AutoGen handles the rest.

Q: What's the real advantage of using this MCP integration with AutoGen's multi-agent setup?

You get specialized agents. An agent that only needs trackdelivery doesn't need to know about openshop. This MCP server provides a clear set of actions that your team of agents can use to negotiate and execute complex workflows.

Let your AI agents debate the best way to run your Ele.me store with AutoGen.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ele.me Open Platform / 饿了么 MCP to AutoGen

Create your Vinkius account to connect Ele.me Open Platform / 饿了么 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 Ele.me Open Platform / 饿了么 with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Let Agents Debate Risky Orders

Create a team of specialized agents. An `OrderManager` agent's goal is to accept new orders fast using `confirm_order`. It works directly with a `RiskAnalyst` agent. Before confirming, the `RiskAnalyst` checks the order against your business rules. If it looks suspicious, it can argue to `cancel_order` instead. The agents debate until they reach a consensus, giving you a smarter, more careful confirmation process.

Balance Store Uptime and Kitchen Capacity

Set up two agents with competing goals. The `GrowthAgent` wants to maximize sales, so it tries to keep the store open using `open_shop`. It converses with the `KitchenManagerAgent`, which monitors order flow with `list_recent_orders`. When the kitchen gets slammed, the `KitchenManagerAgent` will argue to call `close_shop`. They negotiate based on real-time data from this MCP Server, finding the right balance between being open for business and not burning out your staff.

Create a Proactive Customer Service Team

Build a conversation for managing deliveries. A `TrackerAgent` calls `track_delivery` for all active orders. If it detects a stalled delivery, it sends a message to the `ServiceAgent`. The `ServiceAgent` then uses `get_order_detail` to find the customer's info and decides on the next step. It might flag the issue for a human or even use another tool to send an apology. It's a team that solves problems before the customer complains.

Setup guide

Set up Ele.me Open Platform / 饿了么 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 Ele.me Open Platform / 饿了么 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="Ele.me Open Platform / 饿了么_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Ele.me Open Platform / 饿了么 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="Ele.me Open Platform / 饿了么_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Ele.me Open Platform / 饿了么 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 Ele.me Open Platform / 饿了么. 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 Ele.me Open Platform / 饿了么 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 Ele.me Open Platform / 饿了么 MCP in AutoGen

After installing the `autogen-ext[mcp]` package, call `mcp_server_tools` with your Vinkius URL. This MCP function returns a list of tools you can pass directly to your `AssistantAgent`—AutoGen handles the rest.

Yes, that's the core idea. You can have one agent for orders, one for shop status, and another for customer service. They collaborate by passing messages and using the Ele.me tools to act.

They'd debate it. One agent might propose confirming, and another could use `get_order_detail` to check for red flags and argue against it. They reach a group decision instead of following a rigid script.

You get specialized agents. An agent that only needs `track_delivery` doesn't need to know about `open_shop`. This MCP server provides a clear set of actions that your team of agents can use to negotiate and execute complex workflows.

The tool calls that fetch order details or customer comments are handled by the Vinkius sandbox. That data is then passed into the AutoGen conversation. You are in control of where those conversations are logged and stored.

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