How to Use the Kargo MCP in OpenAI Agents SDK

Q: How do I connect the Kargo MCP Server to the OpenAI Agents SDK?

Install the package with pip install openai-agents and initialize MCPServerStreamableHttp pointing to your Vinkius endpoint. Pass this server instance inside the mcpservers list when instantiating your Agent. The SDK auto-discovers the tools, so your agent can immediately call listshipments or getorder.

Q: How does the OpenAI Agents SDK handle high-traffic Kargo MCP tracking requests?

Set cacheToolsList=True in your server parameters to prevent redundant schema lookups. This keeps latency low when your agent is parsing hundreds of orders using listorders or pulling logs with listpayloadlogs during peak warehouse hours.

Q: How does Vinkius protect my carrier contacts and shipment data?

All logistics data, including carrier details from getcarrierinfo and shipment records, runs inside an ephemeral, zero-trust V8 isolate sandbox. No data is stored on Vinkius servers. Your shipping manifests and IoT device states remain strictly between your OpenAI agent and the Kargo platform.

Track shipments and sync loading dock status directly from OpenAI Agents SDK systems with built-in guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kargo MCP to OpenAI Agents SDK

Create your Vinkius account to connect Kargo to OpenAI Agents SDK 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 Kargo with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Guarded OpenAI Agents SDK dispatch updates

By connecting the Kargo MCP Server to your agent, you can run dock operations like `update_logistics` directly from your Python code. The built-in guardrails in this SDK validate every single cargo update before it hits your production database, keeping your shipping manifests clean. You write the safety constraints in Python, and the agent executes the logistics calls. If a model tries to update a container status that doesn't exist, the SDK catches it. It prevents bad data from ever leaving your system.

Real-time gate status checks

Checking physical dock availability is straightforward when your agent queries `get_device_status` and `list_devices`. Your system automatically reroutes incoming trucks based on physical sensor data. You get the best results when running multiple specialized agents. One agent monitors the physical hardware while another handles carrier dispatch. They pass context back and forth, using the OpenAI dashboard to track every single tool call.

Direct carrier routing

Retrieving contact details for delayed drivers is instant when your agent calls `get_carrier_info`. No more manual lookups when a driver is stuck at the gate. Because this MCP Server integration handles tool discovery automatically, you don't have to write custom wrapper code for each endpoint. Just point the SDK to the Vinkius HTTP endpoint, and your agents instantly know how to pull up order sheets and carrier details.

Setup guide

Set up Kargo MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Kargo tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Kargo tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Kargo tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Kargo Agent",
            instructions="You have access to Kargo tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Kargo. 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 Kargo 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 Kargo MCP in OpenAI Agents SDK

Install the package with `pip install openai-agents` and initialize `MCPServerStreamableHttp` pointing to your Vinkius endpoint. Pass this server instance inside the `mcp_servers` list when instantiating your Agent. The SDK auto-discovers the tools, so your agent can immediately call `list_shipments` or `get_order`.

Yes. You can control tool access directly in your Python code by defining specific agent roles. For instance, you can create a gate-keeper agent that only has access to `get_device_status` and `list_devices`, while blocking it from modifying shipments via `update_logistics`.

Set `cacheToolsList=True` in your server parameters to prevent redundant schema lookups. This keeps latency low when your agent is parsing hundreds of orders using `list_orders` or pulling logs with `list_payload_logs` during peak warehouse hours.

No. Vinkius handles the authentication layer for you. Your Python code only needs a single Vinkius endpoint token, which securely routes all requests to Kargo without exposing raw API credentials to your agent.

All logistics data, including carrier details from `get_carrier_info` and shipment records, runs inside an ephemeral, zero-trust V8 isolate sandbox. No data is stored on Vinkius servers. Your shipping manifests and IoT device states remain strictly between your OpenAI agent and the Kargo platform.

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