How to Use the KDniao MCP in AutoGen

Q: How do I configure KDniao tools inside an AutoGen agent?

Install autogen-extmcp and use mcpservertools with your server URL. Pass the resolved tools list to your AssistantAgent constructor to give it full access.

Q: Can AutoGen agents debate which KDniao pickup option to use?

Yes. One agent can argue for onsitepickup for immediate dispatch, while another checks the budget and advocates for preorderpickup to save costs.

Deploy multi-agent logistics teams in AutoGen to debate shipping costs, select carriers, and schedule pickups.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect KDniao MCP to AutoGen

Create your Vinkius account to connect KDniao 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 KDniao with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent MCP Server consensus for China logistics

AutoGen lets you set up specialized agents that debate shipping decisions. A logistics manager agent can propose a carrier, while a finance agent calls `query_shipping_price` to check if it fits the budget. They negotiate the best option before booking. Once they agree, a dispatch agent runs `identify_carrier` and schedules the shipment, ensuring you never overpay for express delivery.

Coordinating waybills and courier pickups

Generating waybills requires precise data. In AutoGen, a verification agent can check the sender and receiver JSON format before passing it to the booking agent, who calls `create_electronic_waybill`. If the warehouse is backed up, a scheduling agent can coordinate with a courier. It chooses between `preorder_pickup` and `onsite_pickup` based on the urgency of the pending orders.

Multi-agent tracking and exception resolution

When shipments run into delays, your agents work together to solve them. A tracking agent calls `track_package` to monitor progress, while an operations agent calculates delays using `get_estimated_arrival`. If a package is stuck, the agents can automatically run `subscribe_tracking` to monitor it closely. They then notify the customer support agent to alert the buyer, handling the entire workflow autonomously.

Setup guide

Set up KDniao 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 KDniao 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="KDniao_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent KDniao 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="KDniao_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent KDniao 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 KDniao. 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 KDniao 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 KDniao MCP in AutoGen

Install `autogen-ext[mcp]` and use `mcp_server_tools` with your server URL. Pass the resolved tools list to your `AssistantAgent` constructor to give it full access.

Yes. One agent can argue for `onsite_pickup` for immediate dispatch, while another checks the budget and advocates for `preorder_pickup` to save costs.

The executing agent receives the API error payload. It can then consult with a supervisor agent to correct the address format or swap the carrier before retrying.

Yes. AutoGen supports Streamable HTTP transport. You can connect your agents to the hosted server endpoint using `StreamableHttpServerParams`.

API keys and sender/receiver addresses are processed in a zero-trust, ephemeral sandbox. No sensitive logistics data is stored on disk, keeping your customer records secure.

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