How to Use the SafeCube Container Tracking MCP in LangChain

Q: Can my LangChain agent handle multiple shipments at once?

Yes. A common pattern is to use listactiveshipments to get all current shipment IDs. Then, your agent can iterate through that list, calling getcontainertracking or getshipmentevents for each one to build a complete picture.

Q: Can I combine SafeCube Container Tracking tools with other LangChain integrations?

Absolutely. You can create a chain where getshipmentevents finds a 'Customs Hold' event, and the next step uses a different tool to send an email to your logistics coordinator. The MCP server tools just become another part of your agent's toolkit.

Build autonomous agents to track maritime shipments and audit logistics events with LangChain.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect SafeCube Container Tracking MCP to LangChain

Create your Vinkius account to connect SafeCube Container Tracking to LangChain — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup SafeCube Container Tracking with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Chain Shipment Audits Step-by-Step

This isn't just about getting data. It's about creating a process. Your LangChain agent can start by calling `list_active_shipments` to get a full manifest of what's on the water. From there, it can loop through each ID, calling `get_container_tracking` to check the current status and location of every single container. Then you build the logic. If a container's status is 'Delayed', the chain automatically triggers a call to `get_shipment_events`. Your agent now has the full history—every port scan, every customs hold—and can decide whether to escalate to a human or just keep monitoring. It’s a completely automated, first-level audit.

Create Self-Correcting Logistics Agents

Real-world APIs fail. It's a fact of life. You can build resilient LangChain agents by making `check_api_status` the first link in any chain. If the SafeCube API is down, the agent doesn't crash—it can pause, notify you, and retry later. This makes your automations robust enough for production. This is how you build an agent that does more than just fetch data. It manages its own workflow. It can decide, based on the output of `get_container_tracking`, whether the next step is to wait, to dig deeper with `get_shipment_events`, or to alert your team on Slack. You define the tools, the agent builds the solution.

Your LangChain MCP Server for Shipping

Connect your ReAct agents to a real-world logistics feed. This MCP server gives your agents the specific tools they need to interact with maritime shipping data directly. No more screen scraping or dealing with fragile, undocumented APIs. Every tool call is observable through LangSmith. You see exactly what your agent asked for (`get_container_tracking` with container ID 'SCZU3948275') and what it got back. This makes debugging complex chains simple, so you can trust the outputs.

Setup guide

Set up SafeCube Container Tracking 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 SafeCube Container Tracking 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({
    "safecube-container-tracking-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 SafeCube Container Tracking 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 SafeCube. 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 SafeCube Container Tracking 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 SafeCube Container Tracking MCP in LangChain

First, install the Vinkius adapter for LangChain. Then, point it to your MCP server endpoint URL. The adapter fetches the tools—`get_container_tracking`, `list_active_shipments`, etc.—and makes them available to your agent.

Yes. A common pattern is to use `list_active_shipments` to get all current shipment IDs. Then, your agent can iterate through that list, calling `get_container_tracking` or `get_shipment_events` for each one to build a complete picture.

Your agent won't fail if you build it correctly. Have it call `check_api_status` first. If the status isn't 'operational', the agent can use that information to decide on its next action, like waiting or sending an alert.

Absolutely. You can create a chain where `get_shipment_events` finds a 'Customs Hold' event, and the next step uses a different tool to send an email to your logistics coordinator. The MCP server tools just become another part of your agent's toolkit.

Your data, like container IDs and shipment event logs, is only passed through Vinkius's ephemeral sandboxes during the API call. We don't store it. Your Vinkius token is the only key to your MCP server, and the connection is always encrypted.

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