How to Use the Aiven MCP in OpenAI Agents SDK

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

Use the MCPServerStreamableHttp class to point your agent directly to the managed URL. The agent auto-discovers all 30 tools during initialization. You just pass the server instance in the mcpservers list when creating your agent.

Deploy self-healing database architectures with the OpenAI Agents SDK and our managed MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Aiven MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Programmatic VPC and database provisioning

The `create_service` tool builds active database clusters across multiple cloud providers without leaving your Python code. Your agent triggers this tool alongside `create_project_vpc` to spin up isolated network environments dynamically. It's a matter of passing the right parameters, and the agent handles the API calls. Let's look at the logs. When the agent calls `list_project_service_types`, it verifies available database engines before executing a build. This prevents runtime errors during deployment pipelines.

Automatic cost and billing guardrails

The `list_billing_groups` tool exposes active billing accounts to prevent your agent from spinning up expensive, unmonitored resources. By combining this with `list_billing_group_invoices`, the OpenAI agent tracks real-time spend before initiating new clusters. Here's the thing: you can enforce strict spending limits in your agent guardrails. If a proposed database exceeds the remaining budget of the active billing group, the agent halts the execution before calling `create_service`.

Safe teardown workflows in OpenAI Agents SDK

The `delete_service` tool terminates running database instances when they are no longer needed by your testing pipelines. Your agent calls this tool to clean up temporary environments, keeping your cloud footprint small and your costs down. To avoid accidental data loss, the agent runs a multi-step check. It runs `list_services` to verify the targets, then checks team permissions via `list_account_teams` before executing `delete_project` or service termination.

Setup guide

Set up Aiven 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 Aiven tools at runtime.
3

Create your Agent

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

Run the agent

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

Use the `MCPServerStreamableHttp` class to point your agent directly to the managed URL. The agent auto-discovers all 30 tools during initialization. You just pass the server instance in the `mcp_servers` list when creating your agent.

Yes, you control this by configuring permissions on the API token passed to the server. If the token lacks access to `delete_service`, the agent cannot execute that tool. This provides a hard boundary that your agent cannot bypass.

It works by assigning infrastructure tasks to a dedicated DevOps agent while keeping other agents focused on code. The DevOps agent uses `list_projects` and `get_service` to feed status reports back to the coordinator agent. This keeps responsibilities clean and isolated.

The server manages connection pooling and retries behind the scenes. If a database provisioning tool like `create_service` takes several minutes, the server returns the initial state and lets your agent poll `get_service` until the cluster is active.

All database connection strings, service configurations, and project metadata pass directly through an ephemeral, zero-trust sandbox. No credentials or cluster configurations are ever written to persistent disks. Your sensitive infrastructure details remain strictly between your agent and the cloud API.

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