A collection of Model Context Protocol (MCP) servers that provide AI assistants, LLMs, and agents with seamless access to IBM Quantum services and Qiskit libraries for quantum computing development and research.
This repository contains production-ready MCP servers that enable AI systems to interact with quantum computing resources through Qiskit. Instead of manually configuring quantum backends, writing boilerplate code, or managing IBM Quantum accounts, AI assistants can now:
- π€ Generate intelligent quantum code with context-aware suggestions
- π Connect to real quantum hardware automatically
- π Analyze quantum backends and find optimal resources
- π Execute quantum circuits and monitor job status
- π‘ Provide quantum computing assistance with expert knowledge
Core Qiskit quantum computing capabilities
Provides quantum circuit creation, manipulation, transpilation, and serialization utilities (QASM3, QPY) for local quantum development using Qiskit
π Directory: ./qiskit-mcp-server/
Intelligent quantum code completion and assistance
Provides access to IBM's Qiskit Code Assistant for AI-assisted quantum programming
π Directory: ./qiskit-code-assistant-mcp-server/
Complete access to IBM Quantum cloud services
Comprehensive interface to IBM Quantum hardware via Qiskit IBM Runtime
π Directory: ./qiskit-ibm-runtime-mcp-server/
AI-powered circuit transpilation
Access to the qiskit-ibm-transpiler library for AI-optimized circuit routing and optimization.
π Directory: ./qiskit-ibm-transpiler-mcp-server/
Reinforcement learning for quantum circuit synthesis
Uses qiskit-gym to train RL models for optimal quantum circuit synthesis, including permutation routing, linear function synthesis, and Clifford circuits.
π Directory: ./qiskit-gym-mcp-server/
Each MCP server includes example code demonstrating how to build AI agents using LangChain:
| Server | Examples |
|---|---|
| Qiskit MCP Server | qiskit-mcp-server/examples/ |
| Qiskit Code Assistant MCP Server | qiskit-code-assistant-mcp-server/examples/ |
| Qiskit IBM Runtime MCP Server | qiskit-ibm-runtime-mcp-server/examples/ |
| Qiskit IBM Transpiler MCP Server | qiskit-ibm-transpiler-mcp-server/examples/ |
| Qiskit Gym MCP Server (Community) | qiskit-gym-mcp-server/examples/ |
Each examples directory contains:
- Jupyter Notebook (
langchain_agent.ipynb) - Interactive tutorial with step-by-step examples - Python Script (
langchain_agent.py) - Command-line agent with multiple LLM provider support
The examples/ directory contains a multi-agent system that combines multiple MCP servers to find the highest achievable Quantum Volume for IBM Quantum backends through actual hardware execution. It demonstrates multi-server orchestration, local tool wrappers to keep large data out of the LLM context, and both single-circuit and full statistical protocol modes. See the examples README for details.
- Python 3.10+ (3.11+ recommended)
- uv package manager (fastest Python package manager)
- IBM Quantum account and API token
- Qiskit Code Assistant access (for code assistant server)
# Install all MCP servers (core + community)
pip install qiskit-mcp-servers[all]
# Install just the core servers (default)
pip install qiskit-mcp-servers
# Install individual servers
pip install qiskit-mcp-servers[qiskit] # Qiskit server only
pip install qiskit-mcp-servers[code-assistant] # Code Assistant server only
pip install qiskit-mcp-servers[runtime] # IBM Runtime server only
pip install qiskit-mcp-servers[transpiler] # IBM Transpiler server only
pip install qiskit-mcp-servers[gym] # Qiskit Gym server only (community)
# Install community servers only
pip install qiskit-mcp-servers[community]Each server is designed to run independently. Choose the server you need:
cd qiskit-mcp-server
uv run qiskit-mcp-servercd qiskit-code-assistant-mcp-server
uv run qiskit-code-assistant-mcp-servercd qiskit-ibm-runtime-mcp-server
uv run qiskit-ibm-runtime-mcp-servercd qiskit-ibm-transpiler-mcp-server
uv run qiskit-ibm-transpiler-mcp-servercd qiskit-gym-mcp-server
uv run qiskit-gym-mcp-server# For IBM Runtime Server
export QISKIT_IBM_TOKEN="your_ibm_quantum_token_here"
# For Code Assistant Server
export QISKIT_IBM_TOKEN="your_ibm_quantum_token_here"
export QCA_TOOL_API_BASE="https://qiskit-code-assistant.quantum.ibm.com"Both servers are compatible with any MCP client. Test interactively with MCP Inspector:
# Test Code Assistant Server
npx @modelcontextprotocol/inspector uv run qiskit-code-assistant-mcp-server
# Test IBM Runtime Server
npx @modelcontextprotocol/inspector uv run qiskit-ibm-runtime-mcp-serverBoth servers follow a consistent, production-ready architecture:
- π Async-first: Built with FastMCP for high-performance async operations
- π§ͺ Test-driven: Comprehensive test suites with 65%+ coverage
- π‘οΈ Type-safe: Full mypy type checking and validation
- π¦ Modern packaging: Standard
pyproject.tomlwith hatchling build system - π§ Developer-friendly: Automated formatting (ruff), linting, and CI/CD
Both servers implement the full Model Context Protocol specification:
- π οΈ Tools: Execute quantum operations (code completion, job submission, backend queries)
- π Resources: Access quantum data (service status, backend information, model details)
- β‘ Real-time: Async operations for responsive AI interactions
- π Secure: Proper authentication and error handling
# Run tests for Code Assistant server
cd qiskit-code-assistant-mcp-server
./run_tests.sh
# Run tests for IBM Runtime server
cd qiskit-ibm-runtime-mcp-server
./run_tests.shBoth servers maintain high code quality standards:
- β
Linting:
ruff checkandruff format - π‘οΈ Type checking:
mypy src/ - π§ͺ Testing:
pytestwith async support and coverage reporting - π CI/CD: GitHub Actions for automated testing
- Model Context Protocol - Understanding MCP
- Qiskit IBM Runtime - Quantum cloud services
- Qiskit Code Assistant - AI code assistance
- MCP Inspector - Interactive testing tool
- FastMCP - High-performance MCP framework
This repository includes AI-generated code and offers comprehensive guidance for AI coding assistants (like IBM Bob, Claude Code, GitHub Copilot, Cursor AI, and others) in AGENTS.md. This helps AI assistants provide more accurate, context-aware suggestions when working with this codebase.
This project is licensed under the Apache License 2.0.