How to Use the Axle MCP in LangChain

Q: Can I trace Axle tool execution inside LangChain?

Yes, every tool call like getvehiclelocation or listloads gets traced automatically if you have LangSmith enabled. You will see the exact inputs, outputs, and latency for every fleet query.

Q: What happens if a driver's hours of service are empty?

The getdriveravailability tool returns a structured payload. If the data is missing, your agent should catch the null value and prompt the user or skip to the next driver.

Get real-time fleet data directly into your LangChain chains to automate dispatch using this MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Axle MCP to LangChain

Create your Vinkius account to connect Axle 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 Axle with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Route loads dynamically using LangChain agents

By running `list_loads`, your agent fetches all pending freight directly into your LangChain decision chains. The agent matches unassigned shipments against driver locations from `list_drivers` and checks remaining service hours with `get_driver_availability` in a single execution loop. Because LangChain handles state transitions between these steps, the agent isn't guessing. It uses the output of one Axle tool to feed the next, culminating in `update_load` to assign the run without human intervention.

Track fleet exceptions via this MCP Server

With `get_vehicle_location`, your agent gets the exact GPS coordinates needed for tracking route exceptions. If a truck goes off-route, the agent pulls up the specific driver profile using `get_driver` to diagnose the delay and check their active duty status. If the delay is due to hold-ups at the receiver, the agent checks `list_documents` to verify the bill of lading before updating the customer. You can track every single one of these tool execution paths inside LangSmith to debug latency or bad agent decisions.

Keep driver duty statuses updated in real time

Executing `update_driver_status` allows your agent to modify driver duty cycles on the fly within your LangChain chains. This keeps your dispatch board accurate without requiring manual data entry from the office staff. Your agent verifies the connection status using `get_account_check` to ensure the API is active before pushing any updates. This prevents failed runs when drivers try to log off duty.

Setup guide

Set up Axle 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 Axle 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({
    "axle-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 Axle 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 Axle. 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 Axle 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 Axle MCP in LangChain

Use the langchain-mcp-adapters package to convert the tools. Initialize the client with the Vinkius HTTP endpoint, call client.get_tools(), and pass them directly into your agent constructor.

Yes, every tool call like get_vehicle_location or list_loads gets traced automatically if you have LangSmith enabled. You will see the exact inputs, outputs, and latency for every fleet query.

You should configure your LangChain runnable with retry logic or rate-limiting wrappers. If tools like list_vehicles return an error, the agent can back off and try again without crashing the entire run.

The get_driver_availability tool returns a structured payload. If the data is missing, your agent should catch the null value and prompt the user or skip to the next driver.

Vinkius hosts the server in a zero-trust, ephemeral V8 sandbox. Your sensitive driver IDs and GPS coordinates retrieved via get_vehicle_location are never stored on the platform and only pass directly to your LangChain client.

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