Where do I find my Business and Facility Slugs?

These unique identifiers are assigned to your organization by Kargo. You can find them in your dashboard settings or by contacting your Kargo account manager.

Can I check the status of physical devices in the warehouse?

Yes! Use the `list_devices` tool to see all IoT equipment at your facility, and `get_device_status` for detailed health metrics and last-seen timestamps for a specific unit.

What is the Unified Endpoint used for?

The Unified Endpoint allows you to push external order or shipment data into the Kargo system for automated processing and real-time visibility updates.

Kargo MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: Kargo
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect Kargo through Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails. no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="Kargo Assistant",
            instructions=(
                "You help users interact with Kargo. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Kargo"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Kargo MCP Server

Connect your Kargo logistics account to your AI agent and optimize your supply chain and loading dock operations through natural conversation.

The OpenAI Agents SDK auto-discovers all 10 tools from Kargo through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns. chain multiple agents where one queries Kargo, another analyzes results, and a third generates reports, all orchestrated through Vinkius.

What you can do

Shipment Tracking — List all shipments for your facility and get real-time status updates and carrier info.
Order Management — Access facility-wide customer orders and their current status.
Deep Inspection — Fetch complete metadata for specific shipments or orders using their unique numbers.
Data Synchronization — Push order and shipment payload data directly to Kargo's Unified Endpoint to keep systems in sync.
Facility & Device Oversight — List all business facilities and monitor the status of active IoT devices (cameras, sensors).
Audit Logs — Review the history of data payloads pushed to the platform.

The Kargo MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Kargo to OpenAI Agents SDK via MCP

Follow these steps to integrate the Kargo MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from Kargo

Why Use OpenAI Agents SDK with the Kargo MCP Server

OpenAI Agents SDK provides unique advantages when paired with Kargo through the Model Context Protocol.

Native MCP integration via `MCPServerSse`, pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

Kargo + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the Kargo MCP Server delivers measurable value.

Automated workflows: build agents that query Kargo, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents. one queries Kargo, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through Kargo tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query Kargo to resolve tickets, look up records, and update statuses without human intervention

Kargo MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect Kargo to OpenAI Agents SDK via MCP:

get_carrier_info

Get carrier contact info

get_device_status

Get specific device status

get_order

Get specific order details

get_shipment

Get specific shipment details

list_devices

List facility IoT devices

list_facilities

List all business facilities

list_orders

List facility orders

list_payload_logs

List sync payload logs

list_shipments

List all shipments at the facility

update_logistics

Sync data to Kargo Unified Endpoint

Example Prompts for Kargo in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with Kargo immediately.

"List all active shipments for my facility."

"Check the status of all IoT devices in the facility."

"Get details for shipment number SHP-2024-05."

Troubleshooting Kargo MCP Server with OpenAI Agents SDK

Common issues when connecting Kargo to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

Kargo + OpenAI Agents SDK FAQ

Common questions about integrating Kargo MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.