How to Use the Dutchie POS MCP in LangChain

Q: Can I chain Dutchie POS inventory checks with other tools in LangChain?

Yes, you can pass the output of listlowstockinventory directly to other tools in a single LangChain run. This allows your agent to fetch low-stock items and draft email orders in one execution sequence.

Run multi-step cannabis retail chains with Dutchie POS tools and LangChain to automate inventory checks and order processing.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dutchie POS MCP to LangChain

Create your Vinkius account to connect Dutchie POS 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 Dutchie POS with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Inventory Audits with LangChain

`list_current_inventory` serves as the starting point for your LangChain ReAct agent to check active Dutchie POS stock levels. The agent takes the raw inventory numbers, identifies discrepancies, and passes those variables directly into the next step of the chain without manual intervention. Your LangChain agent uses the outputs from this tool to trigger automated Dutchie POS reorder chains when quantities drop. LangSmith tracks the exact payload size and latency of each inventory pull so you can optimize your API usage.

Run Automated Order Verifications

`get_order_details` pulls live transaction data directly into your LangChain decision pipelines. The agent reads the Dutchie POS order status, verifies compliance parameters, and decides whether to route the transaction to a compliance officer or approve it. By chaining this tool with your customer databases, the LangChain agent matches purchase histories to flag unusual buying patterns in Dutchie POS. You see the entire execution path in your LangSmith dashboard to verify exactly why an order was flagged.

Search Catalogs and Sync Low Stock

`search_catalog_products` locates specific SKUs to feed real-time pricing data into your LangChain MCP workflows. When a customer asks about a product, the agent searches the Dutchie POS catalog, checks the price, and instantly runs `list_low_stock_inventory` to confirm availability. This setup lets you build conversational retail bots in LangChain that never quote out-of-stock items. The agent handles the multi-step lookup in a single run, keeping your dispensary menu accurate.

Setup guide

Set up Dutchie POS 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 Dutchie POS 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({
    "dutchie-pos-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 Dutchie POS 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 Dutchie POS. 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 Dutchie POS 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 Dutchie POS MCP in LangChain

LangChain manages rate limits by using custom backoff handlers inside your chains. When `list_current_inventory` hits a Dutchie API limit, the framework pauses execution and retries without dropping the agent state.

Yes, you can pass the output of `list_low_stock_inventory` directly to other tools in a single LangChain run. This allows your agent to fetch low-stock items and draft email orders in one execution sequence.

LangSmith automatically logs every tool call made by your LangChain agent, including inputs and outputs from `quick_pos_sales_audit`. You can inspect the exact JSON payloads and execution latency for every dispensary audit.

Yes, you can register the Dutchie POS tools within a LangGraph state machine to build cyclic retail workflows. This lets your agent loop through `list_retail_orders` and update stock levels dynamically.

Your customer records and cannabis purchase history remain safe because Vinkius runs the server in an isolated V8 sandbox. No data is stored on our servers, ensuring your retail compliance logs are never exposed to third parties.

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