How do I get InnoVint API access?

Contact InnoVint support at support@innovint.us to request a Personal Access Token. You'll need an active InnoVint account.

Can I record lab analysis results using this integration?

Yes, you can input new lab readings such as pH, TA, Brix, and free SO2 directly for a specific lot or vessel using natural language, and the AI will post them to the InnoVint API.

Does this support managing multiple wineries under the same account?

Yes, if your InnoVint integrator account has access to multiple wineries, you can scope your API requests to a specific Winery ID to manage lots and vessels across different properties.

InnoVint MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes

Name: InnoVint
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 10 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect InnoVint through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="InnoVint Assistant",
            instructions=(
                "You help users interact with InnoVint. "
                "You have access to 10 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from InnoVint"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About InnoVint MCP Server

Connect your InnoVint winery to any AI agent and transform how your cellar team works — from harvest intake to bottling.

The OpenAI Agents SDK auto-discovers all 10 tools from InnoVint through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries InnoVint, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Lots — Search and track wine lots by varietal, vintage, lot code, or vessel assignment
Vessels — Monitor tanks, barrels, concrete eggs, and amphorae — capacity, fill level, and contents
Lab Analyses — View pH, TA, SO2, Brix, RS, VA, and alcohol readings for any lot over time
Cellar Actions — Track rackings, pump-overs, punchdowns, additions, fining, and filtration history
Wines & Vintages — Browse wine products and navigate production by vintage year
Additives — Reference registered chemicals, enzymes, and fining agents with dosage guidelines
Multi-Winery — Manage multiple wineries from a single AI connection

The InnoVint MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect InnoVint to OpenAI Agents SDK via MCP

Follow these steps to integrate the InnoVint MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 10 tools from InnoVint

Why Use OpenAI Agents SDK with the InnoVint MCP Server

OpenAI Agents SDK provides unique advantages when paired with InnoVint through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

InnoVint + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the InnoVint MCP Server delivers measurable value.

Automated workflows: build agents that query InnoVint, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries InnoVint, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through InnoVint tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query InnoVint to resolve tickets, look up records, and update statuses without human intervention

InnoVint MCP Tools for OpenAI Agents SDK (10)

These 10 tools become available when you connect InnoVint to OpenAI Agents SDK via MCP:

get_lot

The primary data point for any winemaking question. Get full lot details

get_vessel

Essential for barrel program management. Get vessel details

list_actions

Filter by lot to see complete cellar history. List cellar actions

list_additives

With regulatory limits and typical dosage. List additives

list_analyses

Filter by lot to see a specific wine's chemistry over time. List lab analyses

list_vessels

Shows capacity, current contents, fill level, and location. Critical for cellar management and space planning. List tanks and barrels

list_vintages

Navigate wine production by year. List vintages

list_wineries

Multi-winery operations can manage several facilities from one account. List wineries

list_wines

Each with varietal rules, appellation, and production notes. List wine products

search_lots

Returns lot details including volume, vessel assignment, varietal composition, and current status. Essential for tracking individual batches through the winemaking process — from harvest intake to bottling. Search wine lots

Example Prompts for InnoVint in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with InnoVint immediately.

"How is the 2025 Pinot Noir fermentation going?"

"Record a new lab reading for the 2025 Chardonnay: pH is 3.32 and TA is 6.5 g/L."

"Which vessels are currently empty and available for the upcoming harvest?"

Troubleshooting InnoVint MCP Server with OpenAI Agents SDK

Common issues when connecting InnoVint to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

InnoVint + OpenAI Agents SDK FAQ

Common questions about integrating InnoVint MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.