Origin Quantum Open-Sources BenXiaoYuan: An MCP That Connects AI Coding Tools to Real Quantum Computers

On August 22, Origin Quantum announced that its self-developed quantum computing AI assistant BenXiaoYuan has completed a systematic upgrade and is now officially open-sourced, giving developers access to two underlying components:

• QPanda3 quantum programming skill library
• Quantum programming MCP (Model Context Protocol)

The core move: plugging quantum compute into the AI coding ecosystem

The quantum programming MCP is built on the standard MCP protocol and connects Origin Quantum's cloud platform real quantum hardware to the AI ecosystem. Developers who integrate it into AI coding tools such as Claude Code or Cursor can complete a full closed loop of *program generation → submission to real quantum hardware execution*. In Origin Quantum's own words, this equips AI with "real quantum computer hardware."

The QPanda3 skill library, meanwhile, injects a complete quantum programming knowledge system into AI models, letting AI "learn" to write, debug, and optimize quantum programs like a quantum scientist. One component handles knowledge, the other connects to real hardware — together they upgrade BenXiaoYuan from a Q&A tool into a full-pipeline assistant.

Four capabilities after the upgrade

1. Code programming — writing and debugging quantum programs with QPanda3 and VQNet 2. Professional Q&A — integrating foundational concepts, algorithm principles, and product documentation 3. Application scenario assistant — first phase covers quantum chemistry computation: molecular energy, potential energy surfaces, and Jordan-Wigner transforms; quantum machine learning and combinatorial optimization are planned next 4. Deep paper research — systematic analysis of research background, technical approaches, experimental methods, and core conclusions

The entry point is the cloud workbench, with a built-in IDE supporting real-time file viewing and circuit diagrams, enabling "write while asking, verify as you code."

Why it matters: a new answer to the accessibility problem

The real significance is not just another assistant, but a changed solution to the "usability barrier" of quantum computing. Quantum programming historically had two layers of friction:

• Language and abstraction — QPanda3 is not as universally known as Python
• Hardware access — real-machine scheduling and circuit compilation are black boxes

BenXiaoYuan's approach hands the first layer to large language models (knowledge injection via the skill library) and the second to MCP (real hardware becomes a service under a standard protocol). Both layers become usable "like chatting" — arguably the first time quantum compute has been presented to broad developers in this form.

From an industry perspective, this also fills in a piece of the domestic quantum software ecosystem. Origin Quantum's prior output was mostly on the hardware side (e.g., its PSE-CZ series superconducting quantum chips), whereas BenXiaoYuan is a purely software, purely open-source, purely toolchain-level move. Rather than claiming compute performance metrics, the company is betting on a smarter path: for quantum computing to go mainstream, first make the developer toolchain frictionless.

Two open questions worth watching

1. Is quantum chemistry a hedge? As the first use case, is "AI + quantum" stretching into general-purpose compute? Molecular energy calculations can be done with classical approximations — at what system size does real-hardware advantage actually appear? 2. Will the skill library become a cross-platform asset? After open-sourcing, will community members actually connect the QPanda3 skill library to other quantum cloud platforms (e.g., IBM Quantum), turning the skills themselves into a portable, cross-platform asset?

The first question concerns validating real-hardware value; the second concerns whether the ecosystem can gain momentum.