How to Use the SafeCube Container Tracking MCP in AutoGen

Q: How do I use SafeCube Container Tracking tools with my AutoGen agents?

You use the autogen-extmcp library to get the tools from your Vinkius server endpoint. Then you just pass that list of tools to your AssistantAgent's constructor. The adapter handles converting the tool calls into API requests automatically.

Q: Can different AutoGen agents use different SafeCube Container Tracking tools?

Yes. You can configure one agent with access to listactiveshipments and another with access to getshipmentevents. This lets you enforce separation of duties, where one agent finds shipments and another one audits them.

Q: Is it possible for my agents to work together on a single shipment using SafeCube Container Tracking and AutoGen?

Definitely. An agent can call getcontainertracking, post the result to the group chat, and then another agent can use that output to decide whether to call getshipmentevents. AutoGen manages the conversation and state between tool calls.

Assemble a team of AutoGen agents to debate, manage, and audit your container shipments.

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 AutoGen

Create your Vinkius account to connect SafeCube Container Tracking to AutoGen — 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Let Your Agents Debate Logistics

AutoGen's strength is conversation. You can build a team of agents with different jobs. A 'TrackerAgent' could be responsible for periodically calling `list_active_shipments` and `get_container_tracking`, simply reporting the facts into the group chat. Then, a 'LogisticsManagerAgent' can react to those facts. If the tracker reports a delay, the manager agent can take over, call `get_shipment_events` to find the cause, and propose a solution. This creates a system of checks and balances for your supply chain.

Resolve Exceptions with a Multi-Agent Team

A single agent might miss something. With AutoGen, you can have a 'FinanceAgent' and an 'OperationsAgent' analyze the same data. When `get_shipment_events` shows a 'Container Unloaded' event, the OperationsAgent might see a successfully completed job. But the FinanceAgent sees a trigger for revenue recognition and might ask for confirmation. The agents can use the shared context to discuss the event's implications from different angles, leading to a more robust conclusion than one agent could reach alone. This MCP server provides the raw data for their debate.

Build a Resilient AutoGen Supervisor

Your team of agents needs a supervisor. You can create a simple 'SystemStatusAgent' whose only job is to call `check_api_status` every few minutes. If it detects an outage with the SafeCube API, it can broadcast a message to the other agents. This tells the other agents to pause their tasks, like polling `get_container_tracking`, until the service is back online. It's a simple way to make your entire multi-agent system more reliable and prevent them from working with stale or unavailable data.

Setup guide

Set up SafeCube Container Tracking 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 SafeCube Container Tracking 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="SafeCube Container Tracking_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent SafeCube Container Tracking 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="SafeCube Container Tracking_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent SafeCube Container Tracking 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 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 AutoGen

You use the `autogen-ext[mcp]` library to get the tools from your Vinkius server endpoint. Then you just pass that list of tools to your AssistantAgent's constructor. The adapter handles converting the tool calls into API requests automatically.

Yes. You can configure one agent with access to `list_active_shipments` and another with access to `get_shipment_events`. This lets you enforce separation of duties, where one agent finds shipments and another one audits them.

Definitely. An agent can call `get_container_tracking`, post the result to the group chat, and then another agent can use that output to decide whether to call `get_shipment_events`. AutoGen manages the conversation and state between tool calls.

Assign one agent the role of monitoring the API. Have it call `check_api_status` periodically and report the status to the group. This way, the entire team knows if the data source is reliable.

The connection from your AutoGen framework to the MCP server is secured by your Vinkius token. All data, including container and shipment IDs, flows through an isolated execution sandbox on Vinkius that is destroyed after the request. Your logistics data isn't logged or stored by us.

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