aaronsb

Ibm Quantum MCP — AI skill for Claude Code

AI community

MCP servers enabling AI assistants to perform quantum computing experiments using IBM Quantum hardware and simulators, featuring VQE algorithm implementations for molecular energy calculations.

How to install Ibm Quantum MCP

This entry records only its repository, not the path inside it, so there is no exact command to give. Open aaronsb/ibm-quantum-mcp and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Ibm Quantum MCP does

MCP servers enabling AI assistants to perform quantum computing experiments using IBM Quantum hardware and simulators, featuring VQE algorithm implementations for molecular energy calculations.

Alternatives in AI

Sentrux — Real-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improveme 2.9k ★
PaperFarm — Let AI agents run experiments in any repo while you sleep 353 ★
Alibabacloud Ack MCP Server — Alibaba Cloud's ack-mcp-server unifies container operations capabilities, enabling AI assistants and third-par 118 ★

README

Qiskit VQE MCP Servers

MCP (Model Context Protocol) servers that enable AI assistants like Claude to perform quantum computing experiments using IBM Quantum hardware and local simulators.

Overview

This proof-of-concept demonstrates how to make quantum computing accessible through conversational AI. The project provides two specialized MCP servers:

Local Simulation Server (mcp_vqe_server_local.py) - Fast, always-available quantum simulations
Quantum Hardware Server (mcp_vqe_server_quantum.py) - Access to real IBM Quantum processors

Current Status: Proof of Concept

This is an early-stage implementation where the VQE algorithm code is embedded directly within each MCP server. While functional, this architecture has limitations for scaling. The simulation and hardware servers duplicate significant code, making maintenance and feature additions challenging.

Architectural Considerations

For production use or expansion beyond VQE, consider:

Shared quantum algorithm library - Extract VQE and other algorithms into a separate module
Abstract quantum backend interface - Allow switching between simulators and hardware without code duplication
Plugin architecture - Enable adding new algorithms without modifying server code
Result caching layer - Store expensive quantum computations for reuse

Features

🧪 Run Variational Quantum Eigensolver (VQE) for molecular energy calculations
🔬 Support for H₂ and HeH⁺ molecules (easily extensible)
📊 Real-time convergence tracking with matplotlib visualizations
🖥️ Access to IBM's latest Heron R2 quantum processors (156 qubits)
🛡️ Built-in error mitigation and transpilation optimization
📈 Job tracking and result retrieval from IBM Quantum

Quick Start

**Install dependencies:**
```
pip install uv
uv sync
```
**Set up IBM Quantum credentials (for hardware access):**
```
cp .env.example .env
# Edit .env with your IBM Quantum A
```