How to Use the Nabis MCP in LangChain

Build LangChain pipelines that pull live cannabis wholesale data, track invoices, and coordinate deliveries automatically.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Nabis MCP to LangChain

Create your Vinkius account to connect Nabis 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 Nabis with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain wholesale data with LangChain pipelines

The `list_orders` tool exposes Nabis wholesale orders directly to your LangChain agent. Your agent queries this MCP Server endpoint to check shipping statuses and feed those details straight into your customer support workflows. You can route this raw order data to LangSmith for full tracing. This lets you monitor latency and verify exactly how your model processes each transaction.

Automate inventory checks before ordering

The `list_inventory` tool lets your agent pull real-time stock levels across all distribution hubs. You can immediately feed these numbers into a ReAct agent to decide if a retailer needs a restock. Connecting this to `get_warehouse_count` lets you double-check available quantities. Your chain makes decisions based on actual warehouse realities instead of stale spreadsheets.

Verify retailer accounts and invoices

The `get_retailer` tool extracts physical address and license details for any cannabis buyer via this MCP connection. Your agent runs this check before generating new invoices to prevent costly delivery compliance errors. Once verified, the chain calls `list_invoices` to check outstanding balances. This keeps your accounting loop running without manual data entry.

Setup guide

Set up Nabis 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 Nabis 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({
    "nabis-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 Nabis 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 Nabis. 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 Nabis 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 Nabis MCP in LangChain

You use the langchain-mcp-adapters package to bridge them. Simply register the server URL and pass the loaded tools directly into your agent initialization code.

Yes, because the tools output structured data that flows naturally from one step to the next. An agent can check holiday schedules using `get_days_off` and then reschedule a delivery using order data.

LangSmith tracing captures every raw request and response automatically. You will see the exact inputs sent to `get_invoice` and how the model interpreted the payload.

No, Vinkius handles the underlying credentials. Your agent needs only a single endpoint token to run any of the ten available tools.

All requests run inside an ephemeral V8 Isolate sandbox that immediately destroys your session data when the run ends. Your wholesale orders, retailer licenses, and invoice details are never stored on Vinkius servers.

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