How to Use the eCellar MCP in AutoGen

Q: How does this MCP Server handle agent conflicts?

If a security agent flags a transaction retrieved by getorder while a sales agent wants to approve it, AutoGen's debate loop resolves the conflict. They negotiate based on the system instructions you define.

Build multi-agent AutoGen teams that debate and resolve eCellar winery operations and inventory tasks.

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 AutoGen

Create your Vinkius account to connect eCellar to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Multi-Agent eCellar Debates with AutoGen MCP Server

`list_orders` retrieves recent transaction details so your AutoGen agents can review sales performance and fulfillment status. One agent can analyze total revenue while a second agent flags unfulfilled shipments to coordinate daily winery tasks. By debating the data, the agents reach a consensus on which orders need immediate attention. That's how you ensure no high-value club shipment gets stuck in the warehouse.

Coordinate Tasting Room Bookings and Staffing

`list_reservations` displays incoming tasting room bookings for the upcoming weekend. Your scheduling agent uses this data to estimate guest volume, while a logistics agent cross-references it with live inventory. The agents negotiate to determine if you have enough staff and wine bottles ready for the weekend crowd. They use `get_product` to verify which specific vintages are booked for tastings.

Manage Wine Club Allocations and VIP Guests

`search_customers` finds high-value winery guests based on lifetime spend and club status. Your customer service agent shares this profile with a sales agent to draft personalized outreach emails. The agents check `list_clubs` to see which tiers are open for new sign-ups before making recommendations. This automated teamwork helps you target the right club members with exclusive allocation offers.

Setup guide

Set up eCellar MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes eCellar tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="eCellar_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent eCellar data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="eCellar_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent eCellar data")
    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 AutoGen

Register the tools using the MCP adapter and pass them directly to your AssistantAgent. The agents can then call tools like `get_customer` and `list_inventory` during their group chats.

Yes, agents share the conversation context, meaning one agent can run `list_orders` and another can analyze the output. They work together using the same live dataset to solve complex operational problems.

If a security agent flags a transaction retrieved by `get_order` while a sales agent wants to approve it, AutoGen's debate loop resolves the conflict. They negotiate based on the system instructions you define.

The integration supports both stdio and Streamable HTTP transports. Vinkius manages the connection endpoint, so your agents can access tools reliably without complex local networking.

All data transactions run through an ephemeral, zero-trust sandbox. Your customer purchase histories and order records are processed in-memory and never stored, keeping sensitive financial details secure.

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