How to Use the Dada Now Delivery MCP in LangChain

Q: Can a LangChain agent compare shipping rates before booking with Dada Now Delivery?

Yes, your agent can run queryorderfee alongside other shipping tools in the same chain to compare prices. The agent evaluates the returned rates and chooses whether to execute addorder based on your custom logic.

Q: How does LangSmith help debug Dada Now Delivery errors in LangChain?

LangSmith traces the exact payload sent to tools like addorder or cancelorder. If a delivery fails because of a bad city code, you can inspect the inputs of getcitycode to see exactly where the data went wrong.

Let your LangChain agents coordinate local couriers, calculate fees, and dispatch Dada Now Delivery orders in real time.

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 Delivery MCP to LangChain

Create your Vinkius account to connect Dada Now Delivery 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 Delivery with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated dispatch chains

This toolset connects your LangChain agents directly to Dada's local courier network for instant dispatching. By chaining `query_order_fee` directly to `add_order`, your agent calculates the cost of a local run and immediately books the courier if the price sits within your budget. You don't have to write glue code to pass variables between these API steps. The adapter handles the data handoff, letting you trace the exact inputs and outputs in LangSmith. If a dispatch fails, your chain can fallback to `readd_order` or fire a retry event based on the exact error code returned by the MCP Server.

Dynamic shop management in LangGraph

Managing physical storefronts is handled by the `add_shop` and `update_shop` tools inside this server. Keep your retail footprint synchronized during multi-step execution graphs. Your LangChain agent can register a new physical storefront and immediately update operational hours or pickup instructions mid-run. Because LangChain supports multi-server aggregation, you can combine this shipping logic with inventory databases in a single agentic loop. When stock drops to zero, the agent cancels pending pickups using `cancel_order` without human intervention.

Instant delivery tracking for LangChain agents

Tracking deliveries with `query_order_status` lets your LangChain agents monitor couriers in real time. The agent reads the conversation history, grabs the tracking ID, and checks where the driver is located to answer customer shipping queries on the fly. If a customer is unhappy, the agent can trigger `add_complaint` to flag the driver or use `add_tip` to incentivize faster service. You get a fully observable support loop where every tool call is logged and measured for latency.

Setup guide

Set up Dada Now Delivery 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 Delivery 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-delivery-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 Delivery 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. 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 Delivery 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 Delivery MCP in LangChain

You configure the API tokens once in the Vinkius dashboard. LangChain connects to the managed MCP endpoint via `MultiServerMCPClient`, meaning your code never touches raw API keys or delivery credentials.

Yes, your agent can run `query_order_fee` alongside other shipping tools in the same chain to compare prices. The agent evaluates the returned rates and chooses whether to execute `add_order` based on your custom logic.

LangSmith traces the exact payload sent to tools like `add_order` or `cancel_order`. If a delivery fails because of a bad city code, you can inspect the inputs of `get_city_code` to see exactly where the data went wrong.

It runs over a secure, managed HTTP transport. You initialize it using the LangChain MCP adapter, which translates the server's schema into standard tool definitions your agent understands.

Delivery coordinates and customer phone numbers are sent directly to the sandboxed Vinkius runner. The server processes these location details in an ephemeral environment, ensuring no customer PII is stored or cached after the delivery dispatch completes.

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