How to Use the Neon MCP in OpenAI Agents SDK

Q: How do I hook up Neon to the OpenAI Agents SDK?

Install openai-agents and pass the HTTP endpoint to MCPServerStreamableHttpParams. Your OpenAI Agents SDK then auto-discovers all seventeen Neon MCP tools.

Q: Can my OpenAI Agents SDK clean up Neon branches automatically?

Yes, you can program your agent to call deletebranch at the end of a run. This keeps your Neon project clean and prevents resource bloat.

Q: Does the OpenAI Agents SDK support Neon connection string retrieval?

Yes, your agent calls getconnectionuri to fetch the credentials for any specific branch. The OpenAI Agents SDK then passes this string to your application runner.

Q: Can the agent change the main branch of my database?

Yes, the agent uses setprimarybranch via the MCP Server to update which branch acts as the base for new clones. This is useful when promoting a staging branch to production.

Spin up isolated serverless Postgres databases instantly from your OpenAI Agents SDK workflows with zero manual provisioning.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Neon MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Branch databases on the fly using OpenAI Agents SDK

The `create_branch` tool lets your OpenAI Agents SDK spin up a copy-on-write clone of your Neon database instantly. Your OpenAI Agents SDK workflow can test migrations or schema updates on a clean copy of your Neon data without making a mess. Your agent uses `get_connection_uri` to pass the new Neon connection details to downstream python steps. Running integration tests inside an automated OpenAI Agents SDK run becomes trivial since you do not copy physical data bytes.

Automate project setup with this MCP Server

The `create_project` tool provisions a fresh Neon setup containing default branches, roles, and databases automatically. It allows your OpenAI Agents SDK to isolate client data or spin up new tenant environments with a single LLM call. Your agent queries the environment using `list_projects` to keep track of active Neon resources. This MCP Server handles the infrastructure lifecycle while your OpenAI Agents SDK focuses on executing the application code safely.

Safe endpoint routing inside your agent workflows

The `create_endpoint` tool lets your OpenAI Agents SDK configure separate read-only or read-write compute resources on any Neon branch. This ensures your OpenAI Agents SDK routes heavy analytics tasks to a read-only node instead of hammering your primary Neon write database. Your agent secures these environments by calling `create_role` to generate isolated Neon database users with unique passwords. This setup prevents your production credentials from leaking into OpenAI Agents SDK test runs.

Setup guide

Set up Neon 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 Neon tools at runtime.
3

Create your Agent

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

Run the agent

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

Install `openai-agents` and pass the HTTP endpoint to `MCPServerStreamableHttpParams`. Your OpenAI Agents SDK then auto-discovers all seventeen Neon MCP tools.

Yes, you can program your agent to call `delete_branch` at the end of a run. This keeps your Neon project clean and prevents resource bloat.

Yes, your agent calls `get_connection_uri` to fetch the credentials for any specific branch. The OpenAI Agents SDK then passes this string to your application runner.

Yes, the agent uses `set_primary_branch` via the MCP Server to update which branch acts as the base for new clones. This is useful when promoting a staging branch to production.

Your Neon database connection strings, database metadata, and branch names are processed in a zero-trust, ephemeral V8 isolate. Vinkius never stores your database credentials, ensuring your OpenAI Agents SDK only handles data in memory.

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