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

Q: How do I initialize Ele.me Open Platform / 饿了么 inside Google ADK?

Run pip install google-adk. Create a McpToolset using StreamableHttpServerParameters with your Vinkius URL. Pass it to your LlmAgent under the tools parameter.

Q: Can I limit Google ADK to only read Ele.me Open Platform / 饿了么 data?

Yes. Use the toolnames filter when setting up the toolset. You can expose just listrecentorders and hide the mutation commands.

Q: How does Google ADK handle Ele.me Open Platform / 饿了么 delivery tracking?

Your agent calls trackdelivery periodically. It feeds the status updates into Gemini's context window to reason about courier delays.

Q: What happens to customer data during order lookups?

Calling getorderdetail exposes exact delivery coordinates and customer phone numbers. This MCP Server secures this by routing the request through a zero-trust proxy layer. No persistent logs are kept on our infrastructure once the payload reaches your Google Cloud environment.

Connect Gemini agents to Chinese food delivery markets using Google ADK and this managed 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 Google ADK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed Ele.me data into Google ADK

The `get_order_detail` and `get_order_comments` tools pull raw transaction and review data directly into your Gemini context window. You dump thousands of order histories into the prompt. The 1M+ token limit handles the massive payload easily. You tie this straight to BigQuery. Your agent reads the order logs, structures the JSON, and writes it to your data warehouse. You get instant visibility into what sells and what gets returned.

Automate store operations at scale

The `open_shop` and `close_shop` tools give your cloud agents physical control over store availability. A Vertex AI model predicts a demand spike. Your agent triggers a temporary closure to save the kitchen. You verify the current state with `get_shop_info`. If the metadata shows the store is open when it should be closed, the agent corrects it. You restrict the agent to just these tools using the `tool_names` filter in the ADK for this MCP Server.

Process orders and track drivers

The `list_recent_orders` tool fetches the incoming queue. Your agent processes the list and hits `confirm_order` for the valid ones. It rejects flagged transactions using `cancel_order` before the kitchen starts cooking. Once the food leaves, `track_delivery` monitors the courier. Gemini correlates the delivery state with weather data from other APIs. You know exactly why a specific route took longer than expected.

Setup guide

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

Prerequisites

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

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with Ele.me Open Platform / 饿了么 tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="Ele.me Open Platform / 饿了么_agent",
    model="gemini-2.0-flash",
    instruction="You have access to Ele.me Open Platform / 饿了么 tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Run `pip install google-adk`. Create a `McpToolset` using `StreamableHttpServerParameters` with your Vinkius URL. Pass it to your `LlmAgent` under the `tools` parameter.

Yes. Use the `tool_names` filter when setting up the toolset. You can expose just `list_recent_orders` and hide the mutation commands.

Your agent calls `track_delivery` periodically. It feeds the status updates into Gemini's context window to reason about courier delays.

Yes. The MCP Server acts as a standard HTTP transport. Gemini agents on Vertex call these endpoints just like any internal Google tool.

Calling `get_order_detail` exposes exact delivery coordinates and customer phone numbers. This MCP Server secures this by routing the request through a zero-trust proxy layer. No persistent logs are kept on our infrastructure once the payload reaches your Google Cloud 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