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 LangChain 10 tools — connect in under 2 minutes

Name: Kargo
Availability: InStock
Author: Vinkius

python.langchain.com/docs/integrations/tools/mcp

Built by Vinkius GDPR 10 Tools Framework

LangChain is the leading Python framework for composable LLM applications. Connect Kargo through Vinkius and LangChain agents can call every tool natively. combine them with retrievers, memory, and output parsers for sophisticated AI pipelines.

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 langchain_mcp_adapters.client import MultiServerMCPClient
from langchain_openai import ChatOpenAI
from langgraph.prebuilt import create_react_agent

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    async with MultiServerMCPClient({
        "kargo": {
            "transport": "streamable_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,
        )
        response = await agent.ainvoke({
            "messages": [{
                "role": "user",
                "content": "Using Kargo, show me what tools are available.",
            }]
        })
        print(response["messages"][-1].content)

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.

LangChain's ecosystem of 500+ components combines seamlessly with Kargo through native MCP adapters. Connect 10 tools via Vinkius and use ReAct agents, Plan-and-Execute strategies, or custom agent architectures. with LangSmith tracing giving full visibility into every tool call, latency, and token cost.

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 LangChain 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 LangChain via MCP

Follow these steps to integrate the Kargo MCP Server with LangChain.

Install dependencies

Run pip install langchain langchain-mcp-adapters langgraph langchain-openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save the code and run python agent.py

Explore tools

The agent discovers 10 tools from Kargo via MCP

Why Use LangChain with the Kargo MCP Server

LangChain provides unique advantages when paired with Kargo through the Model Context Protocol.

The largest ecosystem of integrations, chains, and agents. combine Kargo MCP tools with 500+ LangChain components

Agent architecture supports ReAct, Plan-and-Execute, and custom strategies with full MCP tool access at every step

LangSmith tracing gives you complete visibility into tool calls, latencies, and token usage for production debugging

Memory and conversation persistence let agents maintain context across Kargo queries for multi-turn workflows

Kargo + LangChain Use Cases

Practical scenarios where LangChain combined with the Kargo MCP Server delivers measurable value.

RAG with live data: combine Kargo tool results with vector store retrievals for answers grounded in both real-time and historical data

Autonomous research agents: LangChain agents query Kargo, synthesize findings, and generate comprehensive research reports

Multi-tool orchestration: chain Kargo tools with web scrapers, databases, and calculators in a single agent run

Production monitoring: use LangSmith to trace every Kargo tool call, measure latency, and optimize your agent's performance

Kargo MCP Tools for LangChain (10)

These 10 tools become available when you connect Kargo to LangChain 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 LangChain

Ready-to-use prompts you can give your LangChain 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 LangChain

Common issues when connecting Kargo to LangChain through the Vinkius, and how to resolve them.

MultiServerMCPClient not found

Install: pip install langchain-mcp-adapters

Kargo + LangChain FAQ

Common questions about integrating Kargo MCP Server with LangChain.

How does LangChain connect to MCP servers?

Use langchain-mcp-adapters to create an MCP client. LangChain discovers all tools and wraps them as native LangChain tools compatible with any agent type.

Which LangChain agent types work with MCP?

All agent types including ReAct, OpenAI Functions, and custom agents work with MCP tools. The tools appear as standard LangChain tools after the adapter wraps them.