How to Use the InnoVint MCP in LlamaIndex

Q: How do I load InnoVint MCP tools into my LlamaIndex agent?

Install llama-index-tools-mcp and initialize the basic client with your Vinkius URL. Call McpToolSpec to convert the endpoints, then pass them to your FunctionAgent as a standard tool list.

Q: Can I limit which InnoVint tools LlamaIndex can access?

Yes, you can use the allowedtools filter during initialization to restrict access. This ensures your agent only calls specific tools like listanalyses while keeping cellar configuration tools locked down.

Q: How does LlamaIndex prevent hallucinations when querying InnoVint lots?

The framework indexes the output of getlot and stores it as node documents. When you query the agent, it retrieves these exact nodes, forcing the LLM to ground its response in your actual winery data.

Q: Where is my sensitive winemaking data stored during indexing?

Your private wine chemistry logs retrieved via listanalyses stay within your local or cloud vector database. Vinkius executes the MCP tool calls inside secure, ephemeral sandboxes, passing the data directly to LlamaIndex without keeping logs.

Index live InnoVint cellar records and lab chemistry directly into your LlamaIndex MCP vector store for hallucination-free RAG.

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 LlamaIndex

Create your Vinkius account to connect InnoVint to LlamaIndex 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 LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a searchable knowledge base of wine lot histories

You use `search_lots` to retrieve real-time volume, vessel assignments, and varietal compositions to feed directly into your LlamaIndex ingestion pipeline. The framework indexes these raw cellar records, transforming live database outputs into searchable vector embeddings. This setup lets your agent answer complex questions about your inventory without hallucinating details. Instead of guessing, LlamaIndex queries the indexed data to give you exact figures on your active Pinot Noir or Chardonnay batches.

Ground RAG applications in live InnoVint lab chemistry

Your agent runs `list_analyses` to pull the historical chemistry of specific lots and merges this data with your winery's standard operating procedures. LlamaIndex combines these external PDF guides and live API results into a single queryable index. When a winemaker asks about volatile acidity trends, the system doesn't rely on generic training data. It checks the actual lab history against your internal protocols to suggest immediate, practical cellar actions.

Track barrel programs with LlamaIndex MCP Server tools

Calling `get_vessel` pulls specific oak profile details, fill levels, and history for any barrel in your program. LlamaIndex parses these structural details, making them instantly searchable alongside your overall vintage logs. This integration allows you to query your barrel inventory using natural language. You find out exactly which cooperages contain your premium Cabernet Sauvignon without digging through separate spreadsheets.

Setup guide

Set up InnoVint MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all InnoVint MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to InnoVint tools.",
)
response = await agent.run("List recent InnoVint data")

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 LlamaIndex

Install `llama-index-tools-mcp` and initialize the basic client with your Vinkius URL. Call `McpToolSpec` to convert the endpoints, then pass them to your `FunctionAgent` as a standard tool list.

Yes, you can use the `allowed_tools` filter during initialization to restrict access. This ensures your agent only calls specific tools like `list_analyses` while keeping cellar configuration tools locked down.

The framework indexes the output of `get_lot` and stores it as node documents. When you query the agent, it retrieves these exact nodes, forcing the LLM to ground its response in your actual winery data.

LlamaIndex shines here by letting you build a unified index. You load your physical cellar SOPs as documents and attach the MCP tools to fetch live vessel volumes simultaneously.

Your private wine chemistry logs retrieved via `list_analyses` stay within your local or cloud vector database. Vinkius executes the MCP tool calls inside secure, ephemeral sandboxes, passing the data directly to LlamaIndex without keeping logs.

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