How to Use the Wine-Searcher MCP in AutoGen

Q: Can Wine-Searcher help with pricing disputes using AutoGen?

Yes. You can set up a debate where one agent relies on marketprice data, challenging another agent that only used general region information to determine value.

Q: Is the region data reliable in Wine-Searcher with AutoGen?

The regioninfo tool offers detailed regional context, which is critical for agent deliberation. Agents treat this input as a core piece of evidence during their debate.

Achieve consensus on wine facts: AutoGen with the Wine-Searcher MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wine-Searcher MCP to AutoGen

Create your Vinkius account to connect Wine-Searcher 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 Wine-Searcher with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate using the MCP Server

Multiple agents can debate a complex query. For example, one agent calls `wine_check` for basic facts while another calls `market_price` to check current value. They then discuss which set of data provides the most accurate conclusion. This consensus-driven approach is perfect when you need multiple perspectives on a single topic, like determining if a wine's score is worth its high price.

Negotiating Wine Recommendations

You can set up agents to negotiate recommendations. One agent uses `grape_info` to define the 'best' variety based on education, while a second agent calls `search_wines` to find the most available option in the user's immediate area. The final answer is a negotiated compromise that satisfies both criteria.

Comparing Producer Strategies

A multi-agent system can tackle brand comparison. One agent analyzes `producer_info` for historical data, while another uses `region_info` to assess the inherent quality of their source region. They then debate which factor is more important when recommending a winery. This simulates expert consultation where different viewpoints converge on one final decision.

Setup guide

Set up Wine-Searcher 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 Wine-Searcher 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="Wine-Searcher_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

    result = await agent.run("List recent Wine-Searcher 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 Wine-Searcher. 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 Wine-Searcher 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 Wine-Searcher MCP in AutoGen

You pass the MCP Server's tools to your AssistantAgent. The agents then use these tools in conversation, debating which tool call is necessary and how its results influence the final conclusion.

Yes. You can set up a debate where one agent relies on `market_price` data, challenging another agent that only used general region information to determine value.

It provides comprehensive data points like grape varieties, global pricing (via `market_price`), and critic scores. The agents use these diverse facts to reach consensus.

The `region_info` tool offers detailed regional context, which is critical for agent deliberation. Agents treat this input as a core piece of evidence during their debate.

The server touches e-commerce pricing and product metadata, including global market pricing and critic scores. It doesn't access personal user accounts or sensitive PII.

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