How to Use the InnoVint MCP in OpenAI Agents SDK

Q: How do I connect the InnoVint MCP Server to my OpenAI Agents SDK?

Install the package with pip install openai-agents and initialize the server using MCPServerStreamableHttp with your Vinkius endpoint. Pass the server instance directly into the mcpservers list of your Agent constructor to enable automatic tool discovery.

Q: Is there a way to speed up tool calls during harvest?

Set cacheToolsList=True in your streamable HTTP parameters. This stops the agent from repeatedly querying the server for the tool schema when it needs to run frequent checks using listanalyses or getvessel.

Build production-grade OpenAI Agents SDK systems that query wine lots, track cellar actions, and manage tank volumes automatically.

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 OpenAI Agents SDK

Create your Vinkius account to connect InnoVint 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 InnoVint with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate wine lot chemistry and vessel space in real-time

Your OpenAI Agents SDK setup can instantly check tank levels and fermentation metrics without manual queries. By hooking up the `list_vessels` and `get_lot` tools on the MCP Server, your agent inspects active fermentation volumes and vessel capacities during peak harvest stress. This lets your system flag volume issues before cellar hands physically move a single gallon of wine. The integration runs inside an async context manager using `MCPServerStreamableHttp`. When your agent needs to audit a specific batch, it calls `search_lots` to map the exact varietal breakdown, preventing accidental field-blend errors before they hit the press.

Coordinate multi-agent chemistry audits with OpenAI Agents

This MCP Server lets you run specialized agents that pass work off to each other based on lab results. A QA agent can pull lab chemistry using `list_analyses`, then hand off to a compliance agent to check legal limits via `list_additives` if sulfur levels drop too low. You configure this by passing the server to the Agent constructor in your Python code. Because the tools are auto-discovered, your agents immediately know how to query `list_actions` to build a complete chronological history of every cellar action performed on a lot.

Secure cellar operations with built-in agent guardrails

Production winemaking cannot tolerate hallucinated tank numbers or wrong additive weights. This server exposes `get_vessel` to let your agent verify physical barrel locations and current fill levels before calculating additions. The SDK's native guardrails validate these tool outputs against your actual winery setup. To keep response times low during busy bottling runs, set `cacheToolsList=True` in your connection params. Your agent gets instant access to `list_wines` and `list_vintages` without making redundant network calls, keeping your cellar dashboard current.

Setup guide

Set up InnoVint 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 InnoVint tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package with `pip install openai-agents` and initialize the server using `MCPServerStreamableHttp` with your Vinkius endpoint. Pass the server instance directly into the `mcp_servers` list of your Agent constructor to enable automatic tool discovery.

Yes, if your account covers multiple facilities, your agent can call `list_wineries` to identify active locations. It can then run targeted queries like `list_vessels` or `search_lots` scoped to a specific winery.

The SDK auto-discovers all ten tools when the agent starts up. Your agent can immediately call `list_actions` to check what cellar work was done, or `get_lot` to inspect the chemistry of a specific batch of Pinot Noir.

Set `cacheToolsList=True` in your streamable HTTP parameters. This stops the agent from repeatedly querying the server for the tool schema when it needs to run frequent checks using `list_analyses` or `get_vessel`.

All chemical analysis logs, lot volumes, and sulfur additive records fetched by `list_analyses` remain within your isolated Vinkius sandboxed MCP environment. Your credentials and lab metrics are never used to train external models, keeping your proprietary blends and cellar actions 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