How to Use the Ninox MCP in OpenAI Agents SDK

Q: How do I connect Ninox to OpenAI Agents SDK?

Install the OpenAI Agents SDK using pip, instantiate MCPServerStreamableHttp with your Vinkius endpoint, and pass it to your Agent constructor to automatically expose Ninox tools like listdatabases.

Q: How does OpenAI Agents SDK handle Ninox script execution errors?

When executeninoxscript fails, the OpenAI Agents SDK captures the exact database error and routes it directly to your tracing dashboard.

Q: Is there an MCP tool to clean up old Ninox data using OpenAI Agents SDK?

Yes, deleterecord lets your OpenAI agent remove specific rows from Ninox tables based on your business logic.

Run production-ready OpenAI Agents SDK workflows directly against your Ninox databases with zero-config MCP tool discovery.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Ninox MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Read schemas with OpenAI Agents SDK

`get_database_schema` inspects the structure of your Ninox tables directly from your OpenAI Agents SDK python runtime. This tool exposes field types and table links so your OpenAI agent can map out Ninox relational data before running writes. Your OpenAI agent uses the Ninox schema info to prevent bad payload errors. By caching the tools list on setup, the OpenAI Agents SDK keeps these schema checks fast without hitting Ninox rate limits.

Safe Ninox record creation using custom guardrails

`create_records` inserts new rows into your Ninox workspace tables while OpenAI's tracing dashboard logs every single property change. You define validation policies in Python to stop the OpenAI agent from writing corrupted data to your Ninox databases. If an OpenAI agent attempts to write a Ninox record with missing fields, the SDK's built-in guardrails intercept the call. This prevents bad inputs from reaching your Ninox tables, keeping your OpenAI agent data clean.

Run complex Ninox scripts via an MCP Server

`execute_ninox_script` runs raw Ninox formula queries directly from your specialized OpenAI agent. This allows you to hand off Ninox database calculation tasks from an OpenAI routing agent to a dedicated data-writing agent. The MCP Server handles the connection protocol securely behind the scenes to link Ninox with OpenAI Agents SDK. Your OpenAI agent gets back the raw Ninox script output, allowing it to make decisions based on complex database calculations.

Setup guide

Set up Ninox 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 Ninox tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the OpenAI Agents SDK using pip, instantiate `MCPServerStreamableHttp` with your Vinkius endpoint, and pass it to your Agent constructor to automatically expose Ninox tools like `list_databases`.

You control access by managing the API token permissions inside your Ninox workspace, which restricts tools like `list_records` for your OpenAI agent.

When `execute_ninox_script` fails, the OpenAI Agents SDK captures the exact database error and routes it directly to your tracing dashboard.

Yes, `delete_record` lets your OpenAI agent remove specific rows from Ninox tables based on your business logic.

Your Ninox relational database records and schemas are processed in memory within Vinkius's zero-trust sandboxed environment before reaching the OpenAI Agents SDK. No data is stored on our servers, ensuring your business records remain private.

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