How to Use the Wine-Searcher MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK handle complex wine lookups with Wine-Searcher?

Your agent uses winecheck as its primary tool. You just ask a natural question—like 'What's good in Napa?'—and it handles pulling data on scores, regions, and pricing from thousands of sources.

Q: Can the OpenAI Agents SDK compare prices across multiple producers using Wine-Searcher?

Absolutely. You can use marketprice or combine winecheck with producerinfo. The agent pulls global data to show you a comprehensive view, letting you spot the best value.

Q: Is the OpenAI Agents SDK good for educational tasks using Wine-Searcher?

Yeah, it's great. You can chain together grapeinfo and regioninfo. The agent builds a full narrative about how grape variety meets terroir to create a specific wine profile.

Q: Does the OpenAI Agents SDK support searching for available wines using Wine-Searcher?

Yes, that's what searchwines is for. It gives you real-time data on availability and scores across multiple merchants right when you need it.

Build production wine intelligence agents with the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect Wine-Searcher 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 Wine-Searcher with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Analyze global pricing and scores.

Need to know if a specific bottle is worth it? The `wine_check` tool lets your agent query 100,000+ merchants for current pricing, critic scores, and availability. It's the main lookup point for any wine question. You can also get high-level market views using `market_price`. This function gives you global data points so you don't just guess at a good deal; your agent shows you verifiable price comparisons.

Research grape types and regions.

If the user is doing sommelier training, they need context. The `grape_info` tool pulls specific data on grape varieties, helping agents write detailed educational content. Similarly, `region_info` provides deep dives into terroir, allowing your agent to explain why a wine tastes like it does based on its origin. Your agent uses this knowledge alongside `producer_info` when comparing brands. It doesn't just list names; it gives context about the winery and how they operate.

Discover available wines instantly.

Don't make your agent guess. The `search_wines` tool lets you hit the database directly, returning matching bottles with scores and current merchant availability. It’s pure discovery. For a deeper dive into specific listings, `wine_check` is still the go-to. You can pass in grape types, regions, or even alcohol content to get an immediate report from the Wine-Searcher MCP Server.

Setup guide

Set up Wine-Searcher 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 Wine-Searcher tools at runtime.
3

Create your Agent

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

Run the agent

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

Your agent uses `wine_check` as its primary tool. You just ask a natural question—like 'What's good in Napa?'—and it handles pulling data on scores, regions, and pricing from thousands of sources.

Absolutely. You can use `market_price` or combine `wine_check` with `producer_info`. The agent pulls global data to show you a comprehensive view, letting you spot the best value.

Yeah, it's great. You can chain together `grape_info` and `region_info`. The agent builds a full narrative about how grape variety meets terroir to create a specific wine profile.

Yes, that's what `search_wines` is for. It gives you real-time data on availability and scores across multiple merchants right when you need it.

It primarily touches commercial metadata, specifically global wine pricing and merchant inventory levels. This is all non-personal product/market data.

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