How to Use the Duoplane MCP in LangChain

Q: How do I connect the Duoplane MCP Server to a LangChain agent?

Install langchain-mcp-adapters and langgraph via pip. Instantiate MultiServerMCPClient with your Duoplane endpoint, call client.gettools(), and pass those tools directly to your agent constructor.

Q: Can LangChain trace Duoplane tool calls during multi-step runs?

Yes, every call to tools like listpurchaseorders or getorderdetails registers automatically in LangSmith. You can inspect the exact inputs, outputs, and latency for every single vendor query your agent executes.

Q: How does LangChain handle Duoplane vendor profile lookups?

Your agent calls getvendorprofile to fetch vendor metadata, which LangChain then injects as context for subsequent steps in your chain. This allows the agent to make routing decisions based on vendor-specific shipping terms.

Run multi-step dropship coordination chains in LangChain using direct Duoplane inventory and purchase order tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Duoplane MCP to LangChain

Create your Vinkius account to connect Duoplane 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 Duoplane with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain PO audits directly into LangChain workflows

`list_unfulfilled_purchase_orders` feeds late order lists directly into your LangChain agent's active memory. The agent checks each delayed shipment, extracts the vendor ID, and immediately triggers `get_vendor_profile` to pull specific communication rules. This multi-step sequence feeds the output of the vendor lookup into downstream email templates. You see the entire execution path inside LangSmith, tracking exactly how your agent resolved the shipping delay without manual file exports.

Multi-server Duoplane inventory checks

`quick_vendor_inventory_audit` runs across multiple supplier catalogs to flag stock discrepancies before they cause overselling. Your LangChain ReAct agent loops through your active supplier list, comparing live counts against your storefront data in a single run. By wrapping this MCP Server in a MultiServerMCPClient, you combine vendor stock checks with database lookups in one unified chain. LangChain manages the state across these calls, letting your agent update your ecommerce platform when it finds a mismatch.

Resolve customer order disputes in LangChain

`search_orders_by_reference` identifies customer purchases using raw transaction IDs from external payment processor webhooks. Your LangChain pipeline ingests the webhook data, searches Duoplane, and passes the order details directly to the next node in the graph. The agent then calls `get_order_details` to verify the fulfillment status of individual items. You get a fully traceable execution tree in LangSmith that shows the exact parameters passed between your customer database and Duoplane.

Setup guide

Set up Duoplane 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 Duoplane 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({
    "duoplane-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 Duoplane 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 Duoplane. 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 Duoplane 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 Duoplane MCP in LangChain

Install `langchain-mcp-adapters` and `langgraph` via pip. Instantiate `MultiServerMCPClient` with your Duoplane endpoint, call `client.get_tools()`, and pass those tools directly to your agent constructor.

Yes, every call to tools like `list_purchase_orders` or `get_order_details` registers automatically in LangSmith. You can inspect the exact inputs, outputs, and latency for every single vendor query your agent executes.

Your agent calls `get_vendor_profile` to fetch vendor metadata, which LangChain then injects as context for subsequent steps in your chain. This allows the agent to make routing decisions based on vendor-specific shipping terms.

Absolutely, you can register this MCP Server alongside database tools or carrier APIs. This allows your agent to fetch an order with `get_order_details` and immediately compare it against shipping carrier data.

Your API credentials and customer order details stay within your local environment or private LangGraph deployment. Vinkius runs the MCP server in an isolated V8 sandbox, ensuring that sensitive purchase orders and vendor profiles never leak to third-party model providers.

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