How to Use the IBM Quantum MCP in CrewAI

Q: Can CrewAI agents share IBM Quantum results?

Yes. CrewAI uses shared memory to pass the output from getjobresult between agents. This allows for multi-step data analysis.

Q: Can I filter tools for specific IBM Quantum agents?

Use the toolfilter feature to restrict access. You might let a research agent only see listbackends while the lead agent handles submitjob.

Deploy a specialized crew of agents to manage IBM Quantum tasks using this 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 IBM Quantum MCP to CrewAI

Create your Vinkius account to connect IBM Quantum to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Collaborative quantum research crew

Assign one agent to `list_backends` while another handles `submit_job`. This division of labor allows your crew to research hardware availability and execute circuits simultaneously. Each agent shares the context of the current job status. This prevents overlapping submissions and optimizes your total queue time.

Autonomous job monitoring

Dedicate a monitor agent to poll `get_job_details` for your entire crew. It keeps the team updated on progress without requiring user input. When a job completes, the monitor signals the analyst agent to grab the output. The workflow continues autonomously until the full experiment finishes.

Automated quantum error recovery

If a circuit fails, the moderator agent uses `cancel_job` to clear the queue. It then logs the error before deciding whether to attempt the run again. This hierarchical execution keeps your quantum pipeline clean. You define the rules, and the crew handles the cleanup automatically.

Setup guide

Set up IBM Quantum MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke IBM Quantum tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="IBM Quantum Analyst",
    goal="Access and analyze IBM Quantum data via MCP.",
    backstory="Expert analyst with direct IBM Quantum access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent IBM Quantum transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="IBM Quantum Analyst",
        goal="Access and analyze IBM Quantum data via MCP.",
        backstory="Expert analyst with direct IBM Quantum access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent IBM Quantum transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the server URL into the mcps list for each agent. This gives them immediate access to the full suite of quantum execution tools.

Yes. CrewAI uses shared memory to pass the output from `get_job_result` between agents. This allows for multi-step data analysis.

You can configure a crew to handle multiple jobs at once. Just be mindful of your IBM account rate limits when setting the agent concurrency.

The server acts as a local bridge. All job results and circuit data are isolated within your agent's memory space and not logged externally.

Use the tool_filter feature to restrict access. You might let a research agent only see `list_backends` while the lead agent handles `submit_job`.

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

Mastra AI sdk-typescript

Start using the IBM Quantum MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started