How to Use the MindsDB (AI Database & Predictors) MCP in OpenAI Agents SDK

Q: How do I check model availability with MindsDB (AI Database & Predictors) and OpenAI Agents SDK?

Your agent runs listmodels to inspect the available predictive algorithms. If it needs details on a specific predictor, it calls getmodel to verify the configuration before running a query.

Run safe, production-grade predictive SQL queries directly inside your OpenAI Agents SDK workflows.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect MindsDB (AI Database & Predictors) MCP to OpenAI Agents SDK

Create your Vinkius account to connect MindsDB (AI Database & Predictors) 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 MindsDB (AI Database & Predictors) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automated SQL routing via OpenAI Agents SDK

The `execute_sql_query` tool lets your OpenAI Agents SDK agent run raw SQL and predictive queries through the MCP Server interface. You must instruct the agent to append explicit LIMIT clauses to prevent context overflow from large result sets. Your agent uses this capability to run predictions or fetch analytics on demand. The SDK handles tool discovery automatically when you pass the server into your agent constructor.

ML model auditing with built-in guardrails

The `list_models` tool retrieves the active machine learning algorithms currently deployed in your MindsDB instance. This allows your agent to verify which predictive engines are online before attempting to generate a forecast. To inspect a specific predictor, the agent calls `get_model` to grab its parameters. OpenAI guardrails validate these actions at runtime, preventing the agent from calling non-existent models.

Schema discovery for multi-agent handoffs

The `list_databases` tool exposes connected data sources so specialized agents can coordinate their data retrieval. For virtual tables, the agent uses `list_views` to read pre-defined SQL views. These tools work together to let your agents map the data environment. If a query fails, the MCP connection remains stable while checking `get_status`.

Setup guide

Set up MindsDB (AI Database & Predictors) 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 MindsDB (AI Database & Predictors) tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate MindsDB (AI Database & Predictors) 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="MindsDB (AI Database & Predictors) Agent",
            instructions="You have access to MindsDB (AI Database & Predictors) 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 MindsDB. 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 MindsDB (AI Database & Predictors) 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 MindsDB (AI Database & Predictors) MCP in OpenAI Agents SDK

You register the MCP server by passing it to the agent constructor using the streamable HTTP parameter class. The SDK auto-discovers the tools, allowing your agent to run SQL queries and pull predictions without manual routing.

Yes, you must instruct your agent to add a LIMIT statement to `execute_sql_query` calls. This prevents large database tables from overloading the LLM context window.

Your agent runs `list_models` to inspect the available predictive algorithms. If it needs details on a specific predictor, it calls `get_model` to verify the configuration before running a query.

No, the SDK handles tool discovery out of the box when you instantiate your server connection. Setting the cache option to true keeps performance fast by avoiding repeated discovery roundtrips.

The connection runs through Vinkius's zero-trust sandboxed environment, keeping your raw SQL statements, prediction outputs, and database credentials isolated. Only the schema definitions and targeted query results are exposed to the agent, ensuring no unauthorized access to your source databases.

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