How to Use the KDniao MCP in CrewAI

Give your CrewAI agents direct access to China's logistics network to automate waybill generation, price checks, and package tracking.

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 CrewAI

Create your Vinkius account to connect KDniao to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-agent routing via MCP Server

The `identify_carrier` tool within this MCP Server lets your CrewAI agents detect shipping providers from raw tracking numbers without human input. You assign a dedicated logistics researcher agent to run it using RequestType 2002. Once the carrier is known, the same agent hits `query_shipping_price` to pull exact rate estimates across different delivery speeds. Chaining these tasks is where the framework shines. A separate financial agent evaluates the pricing data returned by the first agent, decides on the cheapest shipping method, and passes the final decision to your fulfillment crew. You drop the manual rate checks entirely.

Dispatch couriers and print labels

The `create_electronic_waybill` tool gives your execution agents the ability to generate valid shipping labels instantly. Your agent just needs a JSON payload containing the sender and receiver details. Specifically, it requires the Name, Mobile, ProvinceName, CityName, ExpAreaName, and Address. The agent formats the RequestType 1007 call and gets back a printable electronic waybill. After the label exists, another agent in your crew schedules the physical handover. They trigger `preorder_pickup` to book a future courier slot or fire off `onsite_pickup` if the package needs immediate collection. Your agents handle the physical dispatch process from start to finish.

Real-time package monitoring crews

The `track_package` tool lets your customer support crew watch transit updates in real time. Instead of waiting for a buyer to complain about a late delivery, a monitor agent polls the status or sets up a webhook via `subscribe_tracking`. When an exception occurs, the agent catches it immediately. A secondary agent then uses `get_estimated_arrival` to calculate the new delivery window. That agent drafts an apology email with the updated ETA and sends it out before the buyer even notices the delay. You build an active, autonomous support team instead of staring at a passive dashboard.

Setup guide

Set up KDniao MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke KDniao tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="KDniao Analyst",
    goal="Access and analyze KDniao data via MCP.",
    backstory="Expert analyst with direct KDniao access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent KDniao transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="KDniao Analyst",
        goal="Access and analyze KDniao data via MCP.",
        backstory="Expert analyst with direct KDniao access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent KDniao transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the server URL directly into your agent's configuration using `mcps=["https://..."]`. If you need to restrict which logistics tools an agent can access, use `MCPServerHTTP` from `crewai.mcp` with a tool filter. Make sure you run `pip install crewai "crewai[tools]"` first.

Yes. You configure a monitor agent to loop through a database of tracking numbers and call `track_package` for each one. For higher volumes, have your agent use `subscribe_tracking` to listen for webhook events instead of polling the API constantly.

Your agent is likely passing malformed JSON. The KDniao API requires exact string matches for ProvinceName, CityName, and ExpAreaName. Add a validation step to your pipeline to ensure the address data is perfectly structured before the agent submits the request.

It handles it easily. Just give your agent the raw tracking string and tell it to run `identify_carrier`. The tool returns the correct carrier code, which the agent then feeds into other endpoints like pricing or pickup scheduling.

When your agents process receiver details, specifically Name, Mobile, and Address strings, this server routes them directly to the carrier's API inside a V8 Isolate Sandbox. The MCP connection is ephemeral. Once the waybill generates, the memory dumps, leaving zero trace of your customer's physical location on our infrastructure.

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