How to Use the Atlas MCP in OpenAI Agents SDK

Q: How do I authenticate Atlas with the OpenAI Agents SDK?

Provide the Vinkius HTTP endpoint URL for Atlas to your MCPServerStreamableHttpParams configuration block inside the OpenAI Agents SDK. The OpenAI Agents SDK handles the connection handshake automatically, giving your agents instant access to getaccountcheck.

Q: Does this MCP Server support parallel tool calls?

Yes, your OpenAI agent can trigger listtickets and listusers simultaneously. The underlying MCP infrastructure processes these Atlas requests in parallel to speed up your OpenAI agent.

Run safe, production-grade support agents that resolve Atlas tickets using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Atlas MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Safe ticket creation with OpenAI Agents SDK

The `create_ticket` tool lets your OpenAI agent generate new support records directly from user conversations. Running this via our hosted MCP Server lets you set strict guardrails before it posts to Atlas. If a user asks to file a bug, the agent calls `get_account_check` first to verify their status. The OpenAI Agents SDK validation layer then inspects the ticket details before creating the record in Atlas.

Multi-agent handoffs for Atlas customer lookups

Your primary triage agent in the OpenAI Agents SDK uses `list_customers` and `get_customer` to identify the user before routing. Once identified, the OpenAI runtime hands the context off to a specialized billing agent. This handoff pattern keeps your OpenAI Agents SDK system clean because each agent only holds the tools it needs. The billing agent manages tickets using `get_ticket` while the triage agent handles customer lookups over the MCP setup.

Trace help article lookups in your OpenAI dashboard

The `list_articles` tool exposes your entire Atlas knowledge base to your OpenAI agent pool. Every time an agent searches these articles to draft a reply, the call is logged in your OpenAI telemetry dashboard. You see the exact JSON outputs for `list_users` or article searches inside the OpenAI dashboard. This visibility makes debugging failing OpenAI agent runs straightforward when Atlas tickets require complex handoffs.

Setup guide

Set up Atlas 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 Atlas tools at runtime.
3

Create your Agent

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

Run the agent

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

Provide the Vinkius HTTP endpoint URL for Atlas to your `MCPServerStreamableHttpParams` configuration block inside the OpenAI Agents SDK. The OpenAI Agents SDK handles the connection handshake automatically, giving your agents instant access to `get_account_check`.

Yes, you define specific Atlas tool lists when initializing your OpenAI agent constructor. If you only want an OpenAI agent to read data, omit `create_ticket` and only pass `get_ticket` or `list_articles`.

The OpenAI Agents SDK relies on standard Python async error handling to catch Atlas rate limit exceptions. You should implement backoff loops around your OpenAI agent loop to handle heavy Atlas ticket volume.

Yes, your OpenAI agent can trigger `list_tickets` and `list_users` simultaneously. The underlying MCP infrastructure processes these Atlas requests in parallel to speed up your OpenAI agent.

Your Atlas support tickets and customer profiles never persist on Vinkius. All data fetched via the Atlas MCP Server passes through ephemeral V8 sandboxes before returning to your OpenAI agent.

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