How to Use the Dada Now / 达达 MCP in AutoGen

Q: What's the setup for using Dada Now / 达达 with AutoGen?

You'll need the autogen-extmcp package. From there, you use the mcpservertools function with your Vinkius server URL to get the tool list. Just pass that list into the constructor when you create your agents.

Q: Do the agents just execute one tool and stop?

No, they engage in a conversation. An agent might use getshopdetail, present the results to the group, and then another agent might suggest using updateshopinfo based on those results. The process continues until the task is done.

Deploy a team of AutoGen agents to debate, plan, and manage your Dada Now / 达达 delivery operations.

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 AutoGen

Create your Vinkius account to connect Dada Now / 达达 to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Multi-Agent Order Workflows

With AutoGen, you can assign roles. An 'Order Submitter' agent can propose a delivery by preparing a `create_order` call. Before it executes, a 'Validator' agent can inspect the plan, use `query_delivery_fee` to check the cost, and then give its approval. This conversational approach catches errors before they happen. The agents discuss the order details in a chat, using the Dada Now tools to pull facts into their conversation until they reach an agreement. Only then is the order actually placed.

Debate Business Decisions with Live Data

Planning a new shop? Set up a team of agents to debate it. A 'Growth' agent can propose a location and use `add_shop`. A 'Finance' agent immediately challenges it, calling `query_delivery_fee` for that area to report on costs. A 'Logistics' agent chimes in, using `list_supported_cities` to confirm it's a valid territory. This isn't a simple script; it's a simulation of a team meeting. Each agent has a different goal, and they use the tools from this MCP server to argue their points with real-world data from Dada Now.

Reach Consensus on Critical Actions with AutoGen

Deciding whether to cancel an order can be tricky. You can create an 'Analyst' agent that flags a suspicious order and suggests using `cancel_order`. It presents its findings from `get_order_detail`. A 'Support' agent can then argue for confirming with the customer first. This back-and-forth is the core of AutoGen. By having agents with different perspectives debate the action, you get a more considered decision. They don't act until the group conversation reaches a consensus, backed by facts from the Dada Now MCP tools.

Setup guide

Set up Dada Now / 达达 MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Dada Now / 达达 tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Dada Now / 达达_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Dada Now / 达达 data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Dada Now / 达达_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Dada Now / 达达 data")
    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 AutoGen

You provide the same set of tools, retrieved from the MCP server, to each agent in your group chat. The agents can then discuss who should use which tool to accomplish the group's objective.

Yes, that's a primary pattern for AutoGen. The first agent proposes the `create_order` call as part of the conversation. A second agent can then use `get_order_detail` to check the work and confirm back to the group.

You'll need the `autogen-ext[mcp]` package. From there, you use the `mcp_server_tools` function with your Vinkius server URL to get the tool list. Just pass that list into the constructor when you create your agents.

No, they engage in a conversation. An agent might use `get_shop_detail`, present the results to the group, and then another agent might suggest using `update_shop_info` based on those results. The process continues until the task is done.

Yes. Your AutoGen agents access shop and order data through the server, which runs in a dedicated, sandboxed Vinkius environment for each request. All data in transit is encrypted, and your private token is required for any tool to be called.

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