How to Use the Winevybe MCP in AutoGen

Q: Does Winevybe support multi-agent planning with AutoGen?

Yes. Agents can take turns calling tools like getwinedetail and then passing that specific data point to another agent for evaluation or comparison.

Drive consensus on wine decisions using AutoGen's multi-agent deliberation framework.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Winevybe MCP to AutoGen

Create your Vinkius account to connect Winevybe 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 Winevybe with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Wine Pairings with the MCP Server

Instead of just getting one answer, let two agents argue about a pairing. Agent A calls `get_pairings` for a red wine, while Agent B references local knowledge on regional cuisine. They debate which pairing works best. This consensus-driven approach is perfect when the 'right' answer isn't obvious and requires multiple perspectives to weigh.

Multi-Agent Wine Inventory Check for AutoGen

You can set up a system where one agent acts as an inventory manager, calling `get_user_cellar`. Another agent challenges that data by checking the bottle's details using `get_wine_detail` to verify its vintage. They negotiate the final status of the cellar. This simulates complex internal checks and quality control processes.

Deliberate Wine Selection with MCP Server

Need to decide on a purchase? Have one agent search broadly using `search_wines`, while another focuses only on local producers via `get_winery_info`. They discuss the trade-offs—global reach versus local authenticity. The final decision is based on their deliberation. This forces a deep, reasoned outcome instead of just listing results.

Setup guide

Set up Winevybe 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 Winevybe 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="Winevybe_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Winevybe 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="Winevybe_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Winevybe 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 Winevybe. 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 Winevybe 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 Winevybe MCP in AutoGen

Yes. You can set up agents to debate the best selection by having one agent call `get_vintage_scores` and another calling `search_wines`, forcing a reasoned conclusion.

This server touches wine metadata, including regional details (`get_region_info`), user cellar inventory, and producer profiles. All these facts can be used in a debate.

Absolutely. The conversation model ensures transparency by making every agent's tool call visible—whether it was `compare_wines` or `get_reviews`—as part of the deliberation.

Yes. Agents can take turns calling tools like `get_wine_detail` and then passing that specific data point to another agent for evaluation or comparison.

You can set up a security agent whose role is to cross-reference details. It might call `get_user_cellar` and then use another tool to verify every entry against known regional standards.

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