How to Use the Ele.me Open Platform / 饿了么 MCP in OpenAI Agents SDK

Q: How do I connect Ele.me Open Platform / 饿了么 to the OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp instance with your endpoint URL. Pass it into your agent constructor using the mcpservers argument.

Q: Does this integration support real-time delivery tracking?

You poll the trackdelivery endpoint. It returns the current state of the order transit.

Q: How is data privacy handled when checking customer orders?

The getorderdetail tool accesses customer names, addresses, and phone numbers. This MCP Server runs in a V8 Isolate Sandbox. Vinkius destroys the ephemeral environment right after the request finishes, leaving zero residual data behind.

Manage Ele.me store operations and delivery tracking straight from your OpenAI Agents SDK production environment using this 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 Ele.me Open Platform / 饿了么 MCP to OpenAI Agents SDK

Create your Vinkius account to connect Ele.me Open Platform / 饿了么 to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run order logic through your OpenAI Agents SDK

The `confirm_order` and `cancel_order` tools let your agent process incoming Ele.me requests based on kitchen capacity. You poll with `list_recent_orders` to check volume. If the queue backs up, your agent triggers a cancellation or holds confirmation. Handoffs matter here. One agent watches the order queue while a specialized agent handles the disputes. Everything logs to your OpenAI dashboard so you see exactly why a specific order got dropped.

Control shop visibility on the fly

The `open_shop` and `close_shop` tools act as your digital circuit breakers. When the lunch rush hits hard, your agent flips the store offline instantly. It prevents kitchen meltdowns without human intervention. You pull current store metadata using `get_shop_info` to verify what the customer sees. Combine this with `list_shop_categories` to ensure your menu routing matches the actual live inventory via this MCP Server. Built-in guardrails stop the agent from toggling status too fast.

Track driver location and customer sentiment

The `track_delivery` tool pulls live state updates for active drivers. Your agent maps this data against expected prep times. If a driver runs late, the system knows before the customer calls. Post-delivery, the `get_order_comments` tool grabs the actual reviews. You feed these into an analysis pipeline to catch quality drops fast. It pulls the raw text straight from the Ele.me platform.

Setup guide

Set up Ele.me Open Platform / 饿了么 MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Ele.me Open Platform / 饿了么 tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Ele.me Open Platform / 饿了么 tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Ele.me Open Platform / 饿了么 tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Ele.me Open Platform / 饿了么 Agent",
            instructions="You have access to Ele.me Open Platform / 饿了么 tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance with your endpoint URL. Pass it into your agent constructor using the `mcp_servers` argument.

Yes. You handle this through agent instructions and guardrails. Set `cacheToolsList=True` to speed up discovery when loading the MCP Server.

The error bubbles up to your OpenAI dashboard tracing. Your agent can read the failure state and retry or escalate to a human.

You poll the `track_delivery` endpoint. It returns the current state of the order transit.

The `get_order_detail` tool accesses customer names, addresses, and phone numbers. This MCP Server runs in a V8 Isolate Sandbox. Vinkius destroys the ephemeral environment right after the request finishes, leaving zero residual data behind.

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