Quantum Code Validator

A Model Context Protocol (MCP) server for validating quantum computing library code. Currently supports PennyLane, with plans to expand support for other quantum computing libraries in the future.

The Quantum Code Validator is a tool that helps developers ensure their quantum computing code is valid and follows the correct usage patterns for various quantum libraries. It provides static validation of quantum code against official documentation and offers reference documentation lookup capabilities.

- Static Code Validation: Validates quantum code by:

- Checking code syntax using Python'sastmodule
- Verifying code compilation usingpy_compile
- Comparing quantum library method usage against official documentation

- PennyLane: Full support for static validation and reference documentation lookup

- Supported versions: v0.35.0 - v0.41.1

The following quantum computing libraries are planned for future support:

- Qulacs
- Qiskit
- Cirq
- cuQuantum
- And more...

# Example usage result = validate_quantum_method_by_static( code="your_quantum_code_here", version="v0.41.1" # Optional )

# Example usage docs = request_quantum_method_reference( method_name="qml.CNOT", # Method name without arguments version="v0.41.1" # Optional )

git clone https://github.com/yourusername/quantum-code-validator.git cd quantum-code-validator

-

Create and activate a virtual environment:

python -m venv .venv source .venv/bin/activate # On Windows: .venv\Scripts\activate

curl -LsSf https://astral.sh/uv/install.sh | sh

1.1 Load and Parse PennyLane Source Code

Load basic information from PennyLane's source code and save it as JSON files by version. The PennyLane version will be the one installed in the execution environment, so please switch it using the uv command as needed.

uv run scripts/parse_pennylane_api.py ./refdocs/pennylane/raw/v0.41.1.json

Next, we will use an LLM to format the basic information extracted in Step 1 into document information that can be accessed on MCP. Please specify the PennyLane versions to be converted into documents as a comma-separated list. Note that this process uses an LLM, so the "OPENAI_API_KEY" environment variable must be set, and there is a cost of approximately $2.50 per version. The formatting results will be saved in"./refdocs/pennylane/formatted".

uv run scripts/format_docs_by_llm.py v0.41.0,v0.41.1

Finally, by configuring themcp.jsonfile according to the platform and starting the MCP server, the tool becomes available for use with the target tool. As a reference, alinkto the documentation on how to configure it for Claude Desktop is provided.

{ "mcpServers": { "quantum-code-validator": { "command": "uv", "args": [ "--directory", "/your/mcp/server/directory/quantum-code-validator", "run", "server.py", "--transport", "stdio" ] } } }

This project is licensed under the MIT License - see theLICENSEfile for details.

A powerful Model Context Protocol (MCP) server that supercharges your Python development workflow with AI-powered code review, intelligent test generation, and comprehensive test execution.