How to Use the Kargo MCP in LangChain

Q: How do I connect Kargo to LangChain?

Install langchain-mcp-adapters and define a MultiServerMCPClient. Pass the HTTP transport URL for your Kargo instance. Call client.gettools() to bind the logistics operations to your agent.

Build logistics reasoning chains in LangChain to automate your loading docks with live Kargo data.

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 LangChain

Create your Vinkius account to connect Kargo to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Kargo MCP Server tools

Your LangChain agent hits `list_shipments` to find what is sitting at the dock right now. You do not stop there. The agent takes those IDs, loops through `get_shipment` to pull the exact freight details, and feeds that context into your next prompt. That is the point of composable chains. You bind the Kargo MCP Server directly to your LLM, letting it decide when to pull carrier details via `get_carrier_info` based on the shipment status. You get full visibility into every step through LangSmith.

React to physical dock hardware

ReAct agents use `get_device_status` to check if a specific gate sensor is actually online before routing a truck. If the hardware reads offline, the agent knows to pivot. It queries `list_devices` to find an alternative bay. This prevents automated routing from piling trucks into a dead lane. Your LangChain setup treats physical facility hardware as just another tool call. The agent reads the environment, plans a detour, and executes it without you stepping in.

Push logistics updates autonomously

Writing data back to your unified endpoint happens through the `update_logistics` tool. Your agent analyzes incoming orders from `list_orders` and pushes the optimal dock assignments straight to the Kargo platform. You can track every sync attempt using `list_payload_logs`. If an update fails, your chain catches the error, inspects the payload, and tries again. You build resilience right into the agent's logic.

Setup guide

Set up Kargo 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 Kargo 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({
    "kargo-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 Kargo 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 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 LangChain

Install `langchain-mcp-adapters` and define a `MultiServerMCPClient`. Pass the HTTP transport URL for your Kargo instance. Call `client.get_tools()` to bind the logistics operations to your agent.

Yes. LangSmith automatically traces every call to the Kargo MCP Server. You see exactly how many milliseconds it takes to fetch an order or sync a payload.

You manage pagination inside your chain logic. When calling `list_facilities` or `list_shipments`, your agent reads the return data and decides if it needs to request the next batch.

Your agent receives the error from the tool execution. You can write a fallback chain that logs the failure or alerts a human dispatcher.

Vinkius runs the Kargo integration inside an ephemeral V8 Isolate sandbox. When your agent pulls carrier contact details or shipment locations, that data never touches persistent disk storage. The sandbox destroys itself the moment the session ends.

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