How to Use the InnoVint MCP in Pydantic AI

Q: Does Pydantic AI support the deprecated HTTP server classes?

No, you should use the unified MCPToolset class instead of the deprecated HTTP classes. This provides a clean interface for connecting to your external Vinkius MCP Server to query listactions and listanalyses.

Build type-safe Pydantic AI agents that validate wine chemistry, barrel programs, and cellar lot data at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect InnoVint MCP to Pydantic AI

Create your Vinkius account to connect InnoVint 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 InnoVint with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce strict type safety on wine chemistry logs

Winemaking relies on precise numbers, and a single misplaced decimal point in a sulfur addition can ruin a vintage. Using this MCP Server with Pydantic AI guarantees that every piece of lab data returned by `list_analyses` is validated against strict Python type models before your agent can act on it. If the InnoVint API returns an unexpected data format for a pH level or free SO2 measurement, the framework fails loudly. This prevents your agent from making decisions based on corrupted or partial chemistry records.

Validate barrel program details with Pydantic AI

Managing hundreds of oak barrels requires perfect data integrity. Your Pydantic AI agent can call `get_vessel` and `list_vessels` to inspect fill levels, oak types, and current volumes. The framework validates this data against your schemas, ensuring your agent never tries to assign a lot to a non-existent tank. To set this up, install the library using `pip install "pydantic-ai-slim[mcp]"` and initialize `MCPToolset` with your Vinkius HTTP endpoint. Pass the toolset directly to your Agent constructor to begin type-safe cellar tracking.

Track wine lots and cellar actions without silent errors

When tracking wine lots from harvest to bottling, you cannot afford silent failures. Your agent can call `search_lots` to verify volume, varietal composition, and current status. Because Pydantic AI is model-agnostic, you can use these validated tools with OpenAI, Anthropic, or local models. When auditing cellar work, the agent calls `list_actions` to review historical treatments. It can also fetch regulatory limits using `list_additives`, cross-referencing the dosage rules against your active wine profiles from `list_wines` and `list_vintages` with complete type-safe confidence.

Setup guide

Set up InnoVint 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": {
        "innovint-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent InnoVint 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 InnoVint. 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 InnoVint 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 InnoVint MCP in Pydantic AI

Install the slim package with the MCP extra, then initialize an `MCPToolset` pointing to your running server. Pass this toolset into the `toolsets` parameter of your `Agent` to expose tools like `get_lot` and `list_vessels`.

Pydantic AI will immediately throw a validation error at runtime. This loud failure prevents your agent from proceeding with incomplete information when querying critical metrics like lot volumes or vessel fill levels.

Yes, this framework is model-agnostic. You can pair your local model with the toolset to query `search_lots` and `list_wineries` while maintaining strict runtime validation.

No, you should use the unified `MCPToolset` class instead of the deprecated HTTP classes. This provides a clean interface for connecting to your external Vinkius MCP Server to query `list_actions` and `list_analyses`.

All additive formulas, legal dosage limits, and cellar treatment logs fetched via `list_additives` are processed locally within your application memory after passing through our zero-trust MCP gateway. No winery recipe details or chemical addition schedules are stored or logged by Vinkius.

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