How to Use the KuaiDi100 MCP in LangChain

Q: How does LangChain use the KuaiDi100 tools for a full tracking sequence?

You build a chain. It starts with identifycarrier, feeds the output to trackpackage, and if the shipment is active, it calls subscribetracking. It's a simple, logical flow where the output of one KuaiDi100 tool becomes the input for the next.

Q: Can my agent choose between cost and speed?

Yes. Your agent can call queryshippingprice and estimatedeliverytime at the same time. You then define the logic for how it should decide between the two results before it proceeds.

Q: What's the easiest way to get started with KuaiDi100 and LangChain?

Use the MultiServerMCPClient from the LangChain adapter. Point it to your Vinkius endpoint, call client.gettools(), and pass that list directly to your agent. LangChain handles the schema and function calling for you.

Build logistics chains in LangChain to track any package from China using the KuaiDi100 MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect KuaiDi100 MCP to LangChain

Create your Vinkius account to connect KuaiDi100 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 KuaiDi100 with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Tracking and Subscription

This MCP server gives your agent tools to connect logistics actions. Start with `identify_carrier` from just a tracking number. Then, pass that carrier code straight to the `track_package` tool in the next step of your chain. If the package is still in transit, the chain doesn't stop. Your agent can check the status and automatically call `subscribe_tracking` to get webhook updates. You've just built a hands-off tracking sequence that reports back when something changes.

Automate Shipping Decisions

Build a LangChain agent that makes smart shipping choices. It starts by calling `check_carrier_availability` to see who even serves the route. No more guessing. From there, your chain can run `query_shipping_price` and `estimate_delivery_time` in parallel. The agent gets both cost and speed, weighs the options you've defined, and then executes the final `submit_shipping_order` call. It's a complete, automated workflow for creating new shipments.

Provide Visual Tracking Data

Customers want to see their package on a map. This server makes that possible. Your agent can use `get_map_tracking` to pull the latest coordinates and map data for an active shipment. Then, you can chain that output to a notification tool. Send an email or SMS to your customer with a direct link showing exactly where their delivery is. It’s a simple way to offer a feature that used to require a ton of custom code.

Setup guide

Set up KuaiDi100 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 KuaiDi100 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({
    "kuaidi100-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 KuaiDi100 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 KuaiDi100. 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 KuaiDi100 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 KuaiDi100 MCP in LangChain

You build a chain. It starts with `identify_carrier`, feeds the output to `track_package`, and if the shipment is active, it calls `subscribe_tracking`. It's a simple, logical flow where the output of one KuaiDi100 tool becomes the input for the next.

Yes. Your agent can call `query_shipping_price` and `estimate_delivery_time` at the same time. You then define the logic for how it should decide between the two results before it proceeds.

Use the `MultiServerMCPClient` from the LangChain adapter. Point it to your Vinkius endpoint, call `client.get_tools()`, and pass that list directly to your agent. LangChain handles the schema and function calling for you.

Yes, perfectly. Every call your agent makes to a KuaiDi100 tool—like `track_package`—shows up as a distinct step in your LangSmith trace. You can see the exact inputs and outputs for each API call, which makes debugging a chain much faster.

The server only processes the data needed for a specific tool call, like a tracking number for `track_package` or a recipient's phone number for certain carriers. This data passes through Vinkius's ephemeral, zero-trust environment and isn't stored after the API call 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