How to Use the IBM Quantum MCP in LangChain

Q: How do I configure the IBM Quantum MCP Server inside a LangChain agent?

Install langchain-mcp-adapters and initialize the MultiServerMCPClient with the Vinkius endpoint. Pass the tools retrieved from client.gettools() to your createagent call to let your agent execute quantum circuits.

Q: Can LangChain handle long-running jobs submitted via IBM Quantum?

Yes, your agent can poll getjobdetails over time to monitor queue status. Because LangChain supports stateful loops, you can program the agent to wait or execute other tasks while the quantum hardware processes your circuit.

Q: What happens if an IBM Quantum job gets stuck in the queue?

Your LangChain agent can use canceljob to terminate the stuck run. It can then query listbackends to find an active machine with a shorter queue and resubmit the circuit.

Run quantum circuits and track job execution inside your LangChain reasoning loops.

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 LangChain

Create your Vinkius account to connect IBM Quantum to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain execution with the LangChain MCP Server

This MCP Server exposes `submit_job` directly to your LangChain agents to run physical quantum circuits. Your agent checks available hardware with `list_backends` first, then forwards the selected backend name directly into the submission payload. LangSmith traces every step of this multi-step reasoning sequence. You see exactly when the agent calls `get_job_result` and how it handles the raw quantum state tomography data.

Asynchronous job polling in LangChain

The `get_job_details` tool allows your agent to handle asynchronous polling inside a custom execution loop. If a queue grows too long, the agent makes a decision to call `cancel_job` and switch to a faster hardware provider. You configure this logic using LangGraph to build resilient state machines. The agent evaluates the queue latency and automatically routes the circuit payload to a different provider returned by `list_providers`.

Fallback routing based on real-time device stats

The `get_backend_details` tool provides live status updates that your LangChain agent uses to avoid offline quantum processors. By checking gate errors and queue times, the agent routes jobs dynamically. This setup relies on `MultiServerMCPClient` to combine quantum execution with live cloud databases in a single chain. Your agent compares hardware specs on the fly and writes the execution results directly to your storage.

Setup guide

Set up IBM Quantum MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes IBM Quantum tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "ibm-quantum-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent IBM Quantum transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install `langchain-mcp-adapters` and initialize the `MultiServerMCPClient` with the Vinkius endpoint. Pass the tools retrieved from `client.get_tools()` to your `create_agent` call to let your agent execute quantum circuits.

Yes, your agent can poll `get_job_details` over time to monitor queue status. Because LangChain supports stateful loops, you can program the agent to wait or execute other tasks while the quantum hardware processes your circuit.

LangSmith captures every single tool call, including inputs to `submit_job` and outputs from `get_job_result`. You can inspect the exact JSON payloads and latency metrics for every quantum circuit execution in your LangSmith dashboard.

Your LangChain agent can use `cancel_job` to terminate the stuck run. It can then query `list_backends` to find an active machine with a shorter queue and resubmit the circuit.

Vinkius handles your IBM Quantum API tokens in an ephemeral V8 Isolate sandbox, meaning your credentials never touch the LangChain client directly. Only the raw JSON quantum circuit definitions and execution results pass through the MCP connection.

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