A Model Context Protocol Server for Quantum Execution in Hybrid Quantum-HPC Environments

TL;DR

This paper introduces a Model Context Protocol server enabling AI agents, particularly large language models, to autonomously execute quantum algorithms on remote hardware within hybrid quantum-HPC environments.

Contribution

It presents a novel MCP server framework that allows AI-driven quantum workflow execution, bridging the gap between hypothesis formulation and quantum algorithm implementation.

Findings

Successfully executed quantum primitives like sampling and expectation value computation.

Demonstrated autonomous quantum workflow execution via remote hardware and emulators.

Validated AI agents can manage complex hardware interactions through the MCP architecture.

Abstract

The integration of large language models (LLMs) into scientific research is accelerating the realization of autonomous ``AI Scientists.'' While recent advancements have empowered AI to formulate hypotheses and design experiments, a critical gap remains in the execution of these tasks, particularly in the domain of quantum computing (QC). Executing quantum algorithms requires not only generating code but also managing complex computational resources such as QPUs and high-performance computing (HPC) clusters. In this paper, we propose an AI-driven framework specifically designed to bridge this execution gap through the implementation of a Model Context Protocol (MCP) server. Our system enables an LLM agent to process natural language prompts submitted as part of a job, autonomously executing quantum computing workflows by invoking our tools via the MCP. We demonstrate the framework's capability by performing essential quantum algorithmic primitives, including sampling and computation of expectation values. Key technical contributions include the development of an MCP server for quantum execution, a pipeline for interpreting OpenQASM code, an automated workflow with CUDA-Q for the ABCI-Q hybrid platform, and an asynchronous execution pipeline for remote quantum hardware using the Quantinuum emulator via CUDA-Q. This work validates that AI agents can effectively abstract the complexities of hardware interaction through an MCP-based architecture, thereby facilitating the automation of practical quantum research.