How to Use the BasicOps MCP in OpenAI Agents SDK

Q: How do I connect the OpenAI Agents SDK to BasicOps?

You'll need your Vinkius endpoint URL. Just pass it to the MCPServerStreamableHttp constructor in your Python code and add the server instance to your Agent's mcpservers list. The tools are discovered automatically.

Build production agents with the OpenAI SDK to manage BasicOps projects. Built-in guardrails keep your agent's actions in check.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect BasicOps MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Projects Safely

This isn't for prototypes. With the OpenAI Agents SDK, you build agents that follow rules. Your agent can spin up new projects with `create_project` or pull details on existing ones using `get_project`, but OpenAI's guardrails give you a chance to validate the action before it actually runs. No more accidental project creation. You can also set up handoffs between specialized agents. One agent could propose a new project structure after reviewing your active work with `list_projects`, then pass it to another agent with higher permissions for final creation. It's controlled, deliberate automation for your project workflow.

Automate Tasks with Confidence

Let agents handle the busywork of task management. An agent can create a full task list in a new project with `create_task` or modify due dates and assignments with `update_task`. Since tools are auto-discovered, there's no manual mapping to worry about. The real control comes from the full tracing available in your OpenAI dashboard. You can see exactly why your agent decided to close a task or what information it pulled with `get_task`. It's a clear audit trail for every action your agent takes in BasicOps.

Give Agents Team Context with this MCP Server

An agent is only as good as its context. This MCP Server lets your agent see who is on your team with `list_team_users` or check your own profile with `get_account_info`. This stops it from assigning tasks to people who don't exist or getting your own permissions wrong. It can also review project history by pulling discussion threads with `list_task_messages`. This is perfect for building an agent that can summarize progress or get up to speed on a task without you having to explain it. You'll see every one of these lookups in the trace.

Setup guide

Set up BasicOps 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 BasicOps tools at runtime.
3

Create your Agent

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

Run the agent

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

You'll need your Vinkius endpoint URL. Just pass it to the `MCPServerStreamableHttp` constructor in your Python code and add the server instance to your Agent's `mcp_servers` list. The tools are discovered automatically.

Yes. The OpenAI Agents SDK is designed for this. You can implement guardrails in your code to approve or deny actions before they execute, giving you fine-grained control over what the agent can do with your BasicOps data.

It's handled by Vinkius. You get a single endpoint token that authenticates your agent with our managed server. You don't have to deal with OAuth or API keys for BasicOps itself.

Your guardrails are the first line of defense. You can code a check that uses `list_projects` to see if a project with that name already exists before allowing the `create_project` action to proceed.

Your agent will access your BasicOps project, task, and team member data. Vinkius secures this by running each MCP Server in an ephemeral, zero-trust sandbox. The OpenAI SDK adds another layer, letting you inspect and validate every intended action before it touches your data.

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