How to Use the Dada Now / 达达 MCP in LangChain

Q: How do I use Dada Now / 达达 tools in a LangChain agent?

You'll use the MultiServerMCPClient from the LangChain MCP adapter package. After you instantiate the client with your Vinkius endpoint, you just call .gettools() and pass the resulting list directly into your agent's setup.

Q: Can my LangChain agent cancel a Dada Now / 达达 order?

Yes. The cancelorder tool is included. Your agent will need the specific orderid to cancel it, which it could get from a previous call to createorder or by looking up past orders.

Build agents that manage Dada Now logistics from order creation to courier tracking, all inside your LangChain pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dada Now / 达达 MCP to LangChain

Create your Vinkius account to connect Dada Now / 达达 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 Dada Now / 达达 with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Together Delivery Operations

This isn't about calling one tool. It's about building a sequence that runs your logistics. Your LangChain agent can first `query_delivery_fee` for a new destination, use that output to `create_order`, and then immediately call `get_order_detail` to confirm it's been accepted. Because it's LangChain, you see the whole process. Every tool call, input, and output is visible in LangSmith. You can debug exactly where a delivery chain failed, check latencies, and see the agent's reasoning from start to finish.

Automate Your Shop Management

You can build agents that handle your Dada Now storefronts. Give your agent a goal, like 'make sure all Beijing shops have the updated contact info'. It will use `get_shop_detail` to check the current data, see the discrepancy, and then call `update_shop_info` to fix it. This becomes really powerful when you connect it to other data sources in your chain. The agent's decision to update a shop could be triggered by a ticket in your CRM or a message in a Slack channel, creating a fully automated management loop.

Build Smarter Logic with this MCP Server

Good agents have guardrails. Before your agent tries to create an order in a new city, it can use the `list_supported_cities` tool to check if Dada Now even operates there. This prevents unnecessary errors and makes your chains more reliable. This simple check is what separates a basic script from an intelligent agent. The agent isn't just executing commands; it's using the tools from this MCP server to gather facts and make decisions before it acts. That's the core idea of a ReAct agent.

Setup guide

Set up Dada Now / 达达 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 Dada Now / 达达 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({
    "dada-now-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 Dada Now / 达达 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 Dada Now / 达达. 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 Dada Now / 达达 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 Dada Now / 达达 MCP in LangChain

You'll use the `MultiServerMCPClient` from the LangChain MCP adapter package. After you instantiate the client with your Vinkius endpoint, you just call `.get_tools()` and pass the resulting list directly into your agent's setup.

Yes. The `cancel_order` tool is included. Your agent will need the specific `order_id` to cancel it, which it could get from a previous call to `create_order` or by looking up past orders.

The best approach is to make it a two-step chain. First, have the agent call `query_delivery_fee`. Then, feed the output of that tool directly into the parameters for the `create_order` tool call.

Yes, it works out of the box. Every call your agent makes to a Dada Now tool appears as a distinct step in your LangSmith traces, complete with inputs, outputs, and latency data.

Yes. The server only processes the specific shop details and order information required for each tool call. Vinkius runs every MCP Server in an ephemeral sandbox, so your data isn't stored. Your connection is secured by your personal endpoint token.

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