How to Use the eCellar MCP in OpenAI Agents SDK

Q: How do I configure eCellar with the OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp instance with your endpoint URL and pass it to your Agent constructor using the mcpservers array.

Q: Can the eCellar MCP Server handle high-volume order queries?

Yes. The server processes bulk requests through the listorders tool. You handle the pagination logic in your Python code to process thousands of transactions.

Q: Does the OpenAI Agents SDK support caching for eCellar tools?

You can set cacheToolsList=True during initialization. This skips the discovery phase on subsequent runs and speeds up your agent's response times.

Q: How do specialized agents share eCellar data in this SDK?

One agent pulls the profile via getcustomer and hands the context off to a secondary agent. The framework manages the state transfer automatically.

Connect eCellar to OpenAI Agents SDK to build production-grade winery automation with built-in guardrails and full execution tracing.

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 OpenAI Agents SDK

Create your Vinkius account to connect eCellar to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

VIP identification with OpenAI Agents SDK

Your agent pulls real-time buyer profiles using the `search_customers` and `get_customer` tools. It checks lifetime spend, tasting room visits, and purchase history before generating a response. You get the exact CRM data needed to build specialized concierge agents that recognize your top buyers instantly. Managing retention happens through the `list_clubs` and `list_club_members` endpoints. When your agent identifies an at-risk club member, it hands the conversation off to a specialized retention agent. The OpenAI dashboard traces every API call, so you know exactly which data informed the handoff.

Track inventory and fulfillment

The `list_inventory` tool checks multi-location stock levels across your physical cellars and fulfillment centers. Your agent reads this data to prevent overselling highly allocated vintages. If an order fails to ship, the `get_order` and `list_orders` tools pull line items and payment status for immediate reconciliation. You configure the MCP server using `MCPServerStreamableHttp` and pass it to your agent constructor. Setting `cacheToolsList=True` drops the latency on tool discovery. The agent automatically figures out when to check stock versus when to pull a specific order record.

Sync daily tasting room operations

The `list_reservations` tool filters daily bookings by date for your tasting room staff. Your automated assistant matches these bookings against the `list_products` and `get_product` endpoints to ensure you have enough specific varietals chilled and ready for the day's scheduled flights. Built-in guardrails stop the agent from modifying existing reservations or accidentally exposing the wrong wine tiers. You define the safety constraints, and the MCP standard handles the execution. Your tasting room runs on actual data, not guesswork.

Setup guide

Set up eCellar MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all eCellar tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives eCellar tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate eCellar tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="eCellar Agent",
            instructions="You have access to eCellar tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance with your endpoint URL and pass it to your Agent constructor using the `mcp_servers` array.

Yes. The server processes bulk requests through the `list_orders` tool. You handle the pagination logic in your Python code to process thousands of transactions.

You can set `cacheToolsList=True` during initialization. This skips the discovery phase on subsequent runs and speeds up your agent's response times.

One agent pulls the profile via `get_customer` and hands the context off to a secondary agent. The framework manages the state transfer automatically.

The tools read lifetime spend and wine club membership records directly from your database. The connection uses a zero-trust V8 Isolate Sandbox with ephemeral tokens, meaning no customer profiles are stored at rest on the middleware.

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