Qpanda3 Runtime Mcp Server

QPanda3 Runtime MCP Server

[](https://www.python.org/downloads/) [](https://github.com/jlowin/fastmcp) [](https://opensource.org/licenses/Apache-2.0) [](https://originquantum.github.io/qpanda3-runtime-mcp-server/)

A Model Context Protocol (MCP) server that enables AI assistants to interact with Origin Quantum computing services through QPanda3 Runtime.

Features

• Account Management: Configure and manage Origin Quantum cloud account authentication
• Device Management: List and query available QPU devices
• Quantum Computing Tasks: Execute sampling and estimation tasks
• Batch Operations: Run multiple circuits efficiently
• Multi-Objective Decisions: CircuitObservableBinding for complex optimization
• Task Management: Query task status, retrieve results, cancel tasks
• Example Circuits: Provides common quantum circuit example resources

Documentation

| Document | Description | |----------|-------------| | English Docs | English documentation site | | 中文文档 | Chinese documentation site | | [Getting Started](docs/gettingstarted.md) | Complete beginner's guide - START HERE | | [Installation Guide](docs/installation.md) | Detailed installation instructions | | [Quick Start](docs/quickstart.md) | Fast setup for experienced users | | [Configuration](docs/configuration.md) | Environment and client configuration | | [User Guide](docs/userguide/account.md) | Detailed feature documentation | | [API Reference](docs/api/runtime.md) | Auto-generated API documentation |

Installation

One-Click Setup (Recommended)

The project provides setup scripts that automate the entire process:

Linux / macOS:

git clone https://github.com/OriginQ/qpanda3-runtime-mcp-server.git
cd qpanda3-runtime-mcp-server
chmod +x scripts/setup_configure.sh
./scripts/setup_configure.sh

Windows (PowerShell):

git clone https://github.com/OriginQ/qpanda3-runtime-mcp-server.git
cd qpanda3-runtime-mcp-server
.\scripts\setup_configure.ps1

The script handles everything: dependency setup, API key configuration, and MCP client setup.

> See [Installation Guide](docs/installation.md) for manual install options.

Quick Start

# 1. Configure your API key
cp .env.example .env
# Edit .env and set QPANDA3_API_KEY=your_api_key_here

# 2. Run the server
.venv/bin/python -m qpanda3_runtime_mcp_server       # Linux/macOS
# .venv\Scripts\python.exe -m qpanda3_runtime_mcp_server  # Windows

> See [Configuration](docs/configuration.md) for MCP client setup and advanced options.

MCP Tools

Account Management

| Tool | Description | |------|-------------| | setup_origin_quantum_account_tool | Configure Origin Quantum cloud account authentication | | list_saved_accounts_tool | List saved account information (session-based) | | active_account_info_tool | Get currently active account information |

Device Management

| Tool | Description | |------|-------------| | list_qpu_devices_tool | List all available QPU (Quantum Processing Unit) devices | | get_qpu_properties_tool | Get detailed properties of a specific QPU device |

Quantum Computing Tasks

| Tool | Description | |------|-------------| | sample_tool | Execute quantum circuit sampling task on a QPU device | | estimate_tool | Execute expectation estimation task for a quantum circuit | | batch_sample_tool | Batch execute multiple quantum circuit sampling tasks | | batch_estimate_tool | Batch execute estimation tasks for multiple circuits with one observable |

Multi-Objective Decision (CircuitObservableBinding)

| Tool | Description | |------|-------------| | create_circuit_observable_binding_tool | Create a binding for multiple circuits and observables | | add_product_rule_tool | Add Cartesian product combination rule (all combinations) | | add_zip_rule_tool | Add one-to-one combination rule (paired combinations) | | estimate_with_binding_tool | Execute estimation using the created binding | | list_bindings_tool | List all stored CircuitObservableBinding objects | | delete_binding_tool | Delete a stored CircuitObservableBinding object |

Task Management

| Tool | Description | |------|-------------| | get_task_status_tool | Get the execution status of a task (PENDING/RUNNING/DONE/FAILED/CANCELLED) | | get_task_results_tool | Get the computation results of a completed task | | cancel_task_tool | Cancel a running or pending task | | list_my_tasks_tool | List user's recent quantum computing tasks |

MCP Resources

| Resource URI | Description | |--------------|-------------| | qpanda://status | Service status | | circuits://bell-state | Bell state circuit example | | circuits://ghz-state | GHZ state circuit example | | circuits://random | Random number generator circuit | | circuits://superposition | Superposition circuit example |

Example Usage

Configure Account

# Auto-configure via environment variables
# Or call explicitly
await setup_origin_quantum_account_tool(
    api_key="your_api_key"
)

List Devices

devices = await list_qpu_devices_tool()
print(f"Available devices: {devices['total_devices']}")

Execute Sampling Task

# Bell state circuit
circuit = """QINIT 2
CREG 2
H q[0]
CNOT q[0],q[1]
MEASURE q[0],c[0]
MEASURE q[1],c[1]"""

result = await sample_tool(
    circuit=circuit,
    device_id="20",
    shots=1000
)
task_id = result["task_id"]

# Check status and get results
status = await get_task_status_tool(task_id)
if status["task_status"] == "DONE":
    results = await get_task_results_tool(task_id)
    print(f"Measurement results: {results['results']}")

Configure in AI Coding Platforms

> Auto-configure: Use ./scripts/setup_configure.sh --mcp claude-desktop (or --mcp cline, --mcp cursor, etc.)

All clients use the same config format (replace /path/to/... with your actual path):

{
  "mcpServers": {
    "qpanda3-runtime": {
      "command": "/path/to/qpanda3-runtime-mcp-server/.venv/bin/python",
      "args": ["-m", "qpanda3_runtime_mcp_server"],
      "cwd": "/path/to/qpanda3-runtime-mcp-server",
      "env": { "QPANDA3_API_KEY": "your_api_key_here" }
    }
  }
}

| Client | Config File Location | |--------|---------------------| | Claude Code | ~/.claude.json | | Claude Desktop | macOS: ~/Library/Application Support/Claude/claude_desktop_config.json | | Cline | ~/.vscode-server/data/User/globalStorage/saoudrizwan.cline/settings/cline_mcp_settings.json | | Cursor | .cursor/mcp.json (project root) | | Windsurf | ~/.codeium/windsurf/mcp_config.json |

> For more clients (Trae etc.), see [Configuration Guide](docs/configuration.md).

Development

Install Development Dependencies

uv sync --extra dev --extra test

Run Tests

uv run pytest

Code Linting

uv run ruff check .
uv run mypy src/

Build Documentation

# Install documentation dependencies
uv sync --extra docs

# Build documentation (English + Chinese)
./scripts/build-docs.sh

# Local preview with live reload (language switching supported)
mkdocs serve

Project Structure

qpanda3-runtime-mcp-server/
├── src/
│   └── qpanda3_runtime_mcp_server/
│       ├── __init__.py          # Package entry point
│       ├── server.py            # MCP server definition
│       ├── runtime.py           # QPanda3 Runtime core logic
│       └── utils.py             # Utility functions
├── scripts/
│   ├── setup_configure.sh       # One-click setup (Linux/macOS)
│   ├── setup_configure.ps1      # One-click setup (Windows PowerShell)
│   ├── setup_configure.bat      # One-click setup (Windows CMD)
│   ├── build-docs.sh            # Build all documentation
│   └── serve-docs.sh            # Serve docs with live reload
├── tests/
│   ├── __init__.py
│   ├── conftest.py              # pytest configuration
│   ├── test_server.py           # Server tests
│   └── test_runtime.py          # Runtime tests
├── docs/
│   ├── *.md                     # English documentation (default)
│   └── cn/                      # Chinese documentation
├── mkdocs.yml                   # MkDocs configuration (i18n)
├── .github/
│   └── workflows/               # GitHub Actions workflows
├── pyproject.toml               # Project configuration
├── README.md                    # Project documentation
├── LICENSE                      # Apache 2.0 License
├── .env.example                 # Environment variable example
└── .gitignore                   # Git ignore file

Notes

1. Default Server: The server connects to https://qpanda3-runtime.qpanda.cn by default. Set QPANDA3_SERVER_URL to override.
2. Channel: The server uses the qcloud channel by default
3. Async Support: All tool functions are async functions
4. Error Handling: All functions return dictionaries containing a status field
5. Type Hints: Python type hints are used for better code readability

License

This project is licensed under the Apache License 2.0 - see the [LICENSE](LICENSE) file for details.

Related Links

• [QPanda3 Runtime Documentation](qpanda3_runtime.pdf)
• FastMCP Framework
• Model Context Protocol
• Reference Implementation: Qiskit MCP Server

Contributing

See [Contributing Guide](docs/development/contributing.md) for details.

Changelog

See [Changelog](docs/development/changelog.md) for version history.

Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

• Author: OriginQ
• Source: OriginQ/qpanda3-runtime-mcp-server
• License: Apache-2.0

Install and usage instructions live in the source repository linked above.