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

Q: How do I connect my LangChain agent to the Ele.me Open Platform / 饿了么?

Just install the adapter and point the MultiServerMCPClient at your Vinkius endpoint. LangChain's createagent function ingests the Ele.me tools automatically. You're ready to build chains in minutes.

Q: How does LangChain handle custom order logic with the Ele.me Open Platform / 饿了么 tools?

You build it with chains and routers. The agent can use getorderdetail, and based on the contents, a router can decide whether to confirmorder immediately or pass it to another chain for manual approval.

Build event-driven restaurant workflows on the Ele.me platform with LangChain agents.

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 LangChain

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Together Order Operations

Start a chain with `list_recent_orders`. When your agent sees a new order, it automatically uses the order ID to run `get_order_detail`. This is the first link in your custom processing chain. Based on the order details, your agent decides the next step. It can `confirm_order` for standard items or use a router to flag complex orders for human review. You're not just calling a tool; you're building a complete, observable logic pipeline.

Build a Reactive Shop Manager with This MCP Server

Your agent can act like a store manager that never sleeps. It uses `list_recent_orders` in a loop to calculate the current order velocity, giving it a real-time sense of how busy your kitchen is. If orders come in too fast, the agent automatically calls `close_shop`. When things quiet down, it calls `open_shop`. You define the rules; this MCP server gives your agent the tools to execute them 24/7.

Automate Delivery and Service Monitoring

Connect your agent directly to the delivery process. Once an order is confirmed, the agent can periodically call `track_delivery` to log the driver's progress or update an internal dashboard. You can also build a service-oriented chain that runs `get_order_comments` to scan for problems. If it spots negative feedback, it can immediately pull the `get_order_detail` and send a high-priority alert to your team.

Setup guide

Set up Ele.me Open Platform / 饿了么 MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Ele.me Open Platform / 饿了么 tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "eleme-open-platform-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Ele.me Open Platform / 饿了么 transactions"
    })
    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 LangChain

Just install the adapter and point the `MultiServerMCPClient` at your Vinkius endpoint. LangChain's `create_agent` function ingests the Ele.me tools automatically. You're ready to build chains in minutes.

Yes, that's a perfect use case. You can create a ReAct agent that uses `list_recent_orders` to monitor volume and then calls `open_shop` or `close_shop` based on the thresholds you set.

You build it with chains and routers. The agent can use `get_order_detail`, and based on the contents, a router can decide whether to `confirm_order` immediately or pass it to another chain for manual approval.

This MCP server handles the auth and provides standardized tools out of the box. Plus, every tool call is automatically traced in LangSmith, so you get full visibility into your agent's reasoning and performance.

Your agent will process order details and customer comments from Ele.me. All data passes through Vinkius's ephemeral, zero-trust sandbox. Nothing is stored unless you explicitly chain it to your own database.

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