How to Use the Global Wine Score MCP in Pydantic AI

Q: What happens if a wine score is missing during a Pydantic AI query?

If a tool like scoresbyvintage returns data that violates your defined schemas, Pydantic AI raises a validation error. This prevents your agent from acting on incomplete or corrupted wine rating data.

Type-safe wine data validation for your Pydantic AI agents using our verified 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 Pydantic AI

Create your Vinkius account to connect Global Wine Score 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 Global Wine Score with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe wine rating lookups with Pydantic AI

If your agent gets a malformed rating, your entire pricing pipeline can break. Using this MCP Server with Pydantic AI guarantees that every response from `search_wine_scores` is validated against strict Python types before it reaches your agent. If the database returns an unexpected field, the framework raises a validation error immediately instead of letting your agent hallucinate a score. This keeps your wine data clean and your pricing models accurate.

Validate vintage ratings at runtime using Pydantic AI

When building investment bots, you need to know that the year and score match perfectly. Your Pydantic AI agent can query `scores_by_vintage` and parse the output into structured Python models, ensuring that every vintage rating is clean and formatted. Your agent can safely run mathematical formulas on the critic averages. Because the output of `get_latest_scores` is strictly typed, your code can calculate average scores across regions without worrying about missing fields or null values.

Build bulletproof wine discovery agents

Model-agnostic validation means you can switch from OpenAI to Claude without rewriting your wine score schemas. When your Pydantic AI agent calls `get_top_scores`, the framework validates the elite wine list regardless of which LLM you run. You can use `scores_by_color` and `scores_by_country` to build highly targeted search pipelines. The structured responses make it simple to render clean wine score tables in your frontend application without extra parsing code.

Setup guide

Set up Global Wine Score 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": {
        "global-wine-score-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Global Wine Score 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 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 Pydantic AI

The framework wraps the MCP Server tools in runtime validation schemas. When your agent calls `search_wine_scores`, the incoming wine ratings, confidence indexes, and vintage years are strictly validated against Pydantic models.

Yes, Pydantic AI is model-agnostic. You can connect this MCP Server to local models or commercial APIs, and tools like `get_latest_scores` will function identically across all of them.

Use the MCPToolset class with your Vinkius HTTP endpoint. Pass this toolset directly to your Agent instance, and the agent will immediately gain access to `get_top_scores` and other analytical tools.

If a tool like `scores_by_vintage` returns data that violates your defined schemas, Pydantic AI raises a validation error. This prevents your agent from acting on incomplete or corrupted wine rating data.

No. All requests to Global Wine Score are routed through stateless, ephemeral V8 isolates. Your wine search parameters and rating queries are never stored or used for training, keeping your market research confidential.

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