How to Use the IBM Quantum MCP in OpenAI Agents SDK

Q: Can an OpenAI Agents SDK agent select specific IBM Quantum hardware backends?

Yes. The agent uses listbackends to get a list of active QPUs and then calls getbackenddetails to read the configuration.

Q: How does the IBM Quantum integration handle job timeouts in OpenAI Agents SDK?

The agent polls the status using getjobdetails at specified intervals. If the queue wait-time exceeds your threshold, the OpenAI Agents SDK agent calls canceljob to terminate the execution.

Q: Does this setup support private quantum providers?

Yes, the agent can call listproviders to query your specific IBM Quantum access groups, hubs, and projects. This ensures your runs target the dedicated hardware allocations you have purchased.

Run quantum circuits directly from your OpenAI Agents SDK workflows using managed quantum hardware.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IBM Quantum MCP to OpenAI Agents SDK

Create your Vinkius account to connect IBM Quantum 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 IBM Quantum with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage hardware backends in OpenAI Agents SDK

`list_backends` lets your OpenAI Agents SDK agent inspect active IBM Quantum quantum processing units (QPUs) and simulators directly. This prevents your OpenAI agent from sending a heavy 127-qubit circuit to a 5-qubit IBM backend or an offline simulator.

Execute and track quantum jobs with OpenAI guardrails

`submit_job` sends your compiled quantum circuits to the selected IBM hardware provider using the OpenAI Agents SDK safety constraints and our managed MCP Server. Once submitted, the OpenAI agent runs background polling via `get_job_details` to track the execution status.

Retrieve quantum results for OpenAI agent processing

`get_job_result` fetches the raw bitstring counts and quantum state data once the IBM hardware execution completes. Using `list_jobs` and `list_providers`, your OpenAI agent maintains a clear history of past runs across different quantum hubs using this MCP connection.

Setup guide

Set up IBM Quantum 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 IBM Quantum tools at runtime.
3

Create your Agent

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

Run the agent

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

Install openai-agents via pip, then instantiate MCPServerStreamableHttp with your Vinkius endpoint URL. Pass this server instance inside the mcp_servers list when initializing your agent.

Yes. The agent uses list_backends to get a list of active QPUs and then calls get_backend_details to read the configuration.

The agent polls the status using get_job_details at specified intervals. If the queue wait-time exceeds your threshold, the OpenAI Agents SDK agent calls cancel_job to terminate the execution.

Yes, the agent can call list_providers to query your specific IBM Quantum access groups, hubs, and projects. This ensures your runs target the dedicated hardware allocations you have purchased.

Your IBM Quantum API tokens and raw circuit definitions are isolated within Vinkius's V8 sandboxed environment. The server handles authentication at the edge, meaning your OpenAI Agents SDK agent only needs a single secure endpoint token to run jobs.

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