How to Use the Global Wine Score MCP in OpenAI Agents SDK

Get normalized critic data straight to your OpenAI Agents SDK workflows using this secure 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 Global Wine Score MCP to OpenAI Agents SDK

Create your Vinkius account to connect Global Wine Score 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 Global Wine Score with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pull exact critic averages with OpenAI Agents SDK

Your agent needs real data, not hallucinated ratings. By connecting this MCP Server to your OpenAI Agents SDK, your agent can call `search_wine_scores` to pull actual critic averages and confidence ratings instantly. It stops the model from inventing 98-point scores for sub-par vintages. The OpenAI Agents SDK setup takes just a few lines of Python to register the wine tools. You pass the server to your agent constructor, and it immediately knows how to find wines, check their colors, and verify regional data. It uses the `scores_by_color` tool to filter down to the best bottles without writing custom search APIs.

Track vintage performance using OpenAI's agent handoffs

Let one specialized agent handle market trends while another validates specific bottles. With this MCP Server, your OpenAI Agents SDK system can route vintage-specific queries directly to `scores_by_vintage`. The agent gets a clean list of scores grouped by harvest year. This works because the handoff system lets you isolate wine analysis. An agent detects a year in the user's prompt, triggers `get_top_scores` to verify the elite bottles, and hands the clean data back to the main user-facing agent.

Guardrails for your automated wine valuation agents

Running production wine agents means you need strict control over what database queries they run. When your OpenAI Agents SDK calls `get_latest_scores` via this MCP Server, the built-in guardrails validate the incoming parameters before executing the tool. No bad inputs reach the wine database. You get full tracing on your OpenAI dashboard for every single wine score lookup. If an agent tries to run `scores_by_country` with an invalid country name, you see exactly where the validation failed in your logs.

Setup guide

Set up Global Wine Score 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 Global Wine Score tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Global Wine Score 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="Global Wine Score Agent",
            instructions="You have access to Global Wine Score 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 Global Wine Score. 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 Global Wine Score 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 Global Wine Score MCP in OpenAI Agents SDK

It aggregates ratings from top critics and normalizes them to a 100-point scale. When your OpenAI Agents SDK calls `search_wine_scores`, the model receives a clean, confidence-weighted average instead of noisy, conflicting critic reviews.

Yes, you control this at the agent level when initializing the server connection. If you only want your agent to research specific years, you can restrict its access so it only calls `scores_by_vintage` and ignores the other five tools.

You pass your Vinkius endpoint token when creating the MCPServerStreamableHttp instance. The SDK handles the connection under the hood, exposing tools like `get_top_scores` directly to your MCP client.

No, OpenAI Agents SDK auto-discovers the tools. The model reads the descriptions for `scores_by_country` and knows exactly when to call it based on the user's natural language request.

Your wine search queries and score requests go through Vinkius's ephemeral sandbox. We do not store your private search logs or wine preference data; we simply fetch the normalized score from the database and pass it to your OpenAI Agents SDK.

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