How to Use the eCellar MCP in LangChain

Q: Can I trace eCellar tool calls in LangSmith?

Yes, every tool call like getcustomer or listorders runs through standard LangChain runnables. This means you get full visibility into latency, input parameters, and exact payloads inside your LangSmith dashboard.

Run multi-step winery operations chains in LangChain using direct eCellar live database tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect eCellar MCP to LangChain

Create your Vinkius account to connect eCellar 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 eCellar with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Orchestrate LangChain Chains with eCellar MCP Server

`list_reservations` pulls today's tasting room schedule directly into your LangChain run, feeding the guest list straight into your next operational step. Your agent reads this list and instantly triggers `search_customers` to pull up lifetime spend and club status for every arriving guest. This chain links your physical tasting room bookings directly to your CRM data. LangSmith traces every step of the tool execution, showing you exactly how customer records are fetched and passed along without manual data entry.

Automate Wine Club Allocations and Orders

`list_clubs` retrieves your active wine club tiers so your agent can verify membership levels before processing transactions. Once the agent identifies the correct tier, it uses `list_club_members` to match members with their specific shipment preferences. The agent then runs `get_product` to check pricing and applies the correct club discounts before generating the final draft. This multi-step reasoning ensures club members always get their allocated bottles and correct pricing.

Reconcile Inventory Against Live Orders

`list_inventory` displays current stock levels across all physical winery locations to prevent overselling premium vintages. Your agent compares these numbers against pending sales retrieved via `list_orders` to flag discrepancies. If stock runs low, the agent pulls product details using `get_product` to find alternative bottles for the customer. This automated reconciliation keeps your physical cellar and online store in perfect sync.

Setup guide

Set up eCellar 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 eCellar 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({
    "ecellar-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 eCellar 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 eCellar. 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 eCellar 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 eCellar MCP in LangChain

Install the MCP adapter package and initialize the client with your Vinkius endpoint. It's as simple as passing the tools retrieved from the client directly into your agent constructor to start querying wine data.

Yes, every tool call like `get_customer` or `list_orders` runs through standard LangChain runnables. This means you get full visibility into latency, input parameters, and exact payloads inside your LangSmith dashboard.

Your agent uses ReAct loops to decide which tools to call sequentially. For example, it can search a customer with `search_customers`, grab their order history with `list_orders`, and look up their club status in one run.

The framework catches the API error and passes the failure message back to the agent. Your agent can then retry the call, log the error, or choose an alternative path like checking cached inventory.

Vinkius runs this MCP server in an isolated sandbox, ensuring your winery customer profiles and purchase history remain private. No customer records or order details are stored or logged on external servers during execution.

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