How to Use the Wine Pairing & Sommelier MCP in Pydantic AI

Ensure perfect data integrity when pairing wines with Pydantic AI's runtime validation layer.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Wine Pairing & Sommelier MCP to Pydantic AI

Create your Vinkius account to connect Wine Pairing & Sommelier to Pydantic AI 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 Pairing & Sommelier with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Reliable Wine Pairing (MCP Server)

The main goal of `get_wine_pairing` is to give you structured results: a wine, a food item, ratings, and prices. With Pydantic AI, if the server sends back unexpected data, your agent fails loudly. No silent corruption. You get guaranteed, predictable output every time you run the pairing tool.

Structured Dish Recommendations

Need to pair a wine (like Pinot Noir) with a dish? Use `get_dish_for_wine`. The resulting data is validated against Pydantic models. You're never going to get a field you didn't expect, which keeps your downstream code clean. This model-agnostic approach means the pairing logic works whether you use OpenAI or Gemini underneath.

Validated Wine Product Lists

When running `recommend_wines`, you get a list of specific products. Pydantic validation ensures that every product record has all required fields—like the name, rating, and price—before your agent processes it. Correctness is paramount here; this framework makes sure your data is rock solid.

Setup guide

Set up Wine Pairing & Sommelier MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "wine-pairing-sommelier-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Wine Pairing & Sommelier tools.",
)

result = await agent.run("List recent Wine Pairing & Sommelier transactions")
print(result.output)

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 Spoonacular Wine. 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 Pairing & Sommelier 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 Pairing & Sommelier MCP in Pydantic AI

It validates the schema of every single response from the MCP Server. If a tool—like `get_wine_pairing`—returns data that doesn't match the expected types, your agent raises a clear error instead of failing silently.

Yes. Since it validates against defined models, you can enforce strict structures around things like pricing and ratings. This is crucial when handling detailed wine inventory.

The agent immediately fails validation, giving you a clear error message about which field was wrong. You never risk passing bad or incomplete data to your application logic.

It handles structured types: wine names, dish descriptions, ratings (float), and prices (currency). These are all defined and validated by the framework.

Absolutely. Because every tool's output is guaranteed to be correctly typed, one agent can hand off reliable data to another agent for subsequent steps.

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