How to Use the eCellar MCP in LlamaIndex

Q: How do I index eCellar data using the LlamaIndex MCP integration?

Use the MCP tool spec to load tools like listproducts and listinventory into your LlamaIndex environment. From there, you can run the tools to fetch data and ingest the outputs directly into your document store.

Q: Can I use LlamaIndex to search eCellar customer history?

Yes, you can use searchcustomers to pull detailed customer profiles into your index. This allows your agent to perform semantic searches over purchase history, tasting room visits, and lifetime spend.

Q: How does this MCP Server prevent hallucinated wine details?

By querying live data through getproduct, LlamaIndex grounds its responses in your actual database. The agent relies on current pricing and bottle specs instead of guessing or using stale training data.

Index live eCellar wine data directly into LlamaIndex vector stores for grounded, accurate RAG queries.

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 LlamaIndex

Create your Vinkius account to connect eCellar to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Live eCellar Wine Data into LlamaIndex MCP Server

`list_products` pulls your complete wine catalog directly into LlamaIndex to build a searchable knowledge base. Your agent indexes these product descriptions and pricing details, making them instantly searchable via semantic queries. This setup lets your agent answer complex questions about your vintages using actual, live catalog data. There's no more outdated product sheets—just direct, grounded answers from your active database.

Query Active Wine Club and Customer Records

`list_club_members` fetches your active wine club rosters to help you analyze retention and engagement trends. By indexing this data, your agent can cross-reference member lists with purchase patterns retrieved from `list_orders`. You can ask your agent to find members who haven't ordered in six months, and it will query the index to generate a targeted list. This turns raw operational data into actionable insights for your tasting room staff.

Track Winery Reservations and Inventory Status

`list_reservations` retrieves daily tasting room bookings so your agent can prepare the hosting team for incoming guests. The agent combines this schedule with live inventory data fetched via `list_inventory` to ensure you have enough bottles prepped. If a guest has a reservation, the agent runs `get_customer` to find their lifetime spend and favorite varietals. This gives your staff the exact context they need to deliver a personalized tasting experience.

Setup guide

Set up eCellar MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all eCellar MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to eCellar tools.",
)
response = await agent.run("List recent eCellar data")

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 LlamaIndex

Use the MCP tool spec to load tools like `list_products` and `list_inventory` into your LlamaIndex environment. From there, you can run the tools to fetch data and ingest the outputs directly into your document store.

Yes, you can use `search_customers` to pull detailed customer profiles into your index. This allows your agent to perform semantic searches over purchase history, tasting room visits, and lifetime spend.

By querying live data through `get_product`, LlamaIndex grounds its responses in your actual database. The agent relies on current pricing and bottle specs instead of guessing or using stale training data.

Yes, you can pass an allowed tools list when initializing the client to restrict access. This lets you expose only public catalog tools like `list_products` while keeping customer databases hidden.

Your inventory counts and wine pricing are protected by a secure, zero-trust environment that handles authorization securely. This sensitive operational data is never exposed to public models or saved on third-party 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