Python code analysis for AI agents: complexity, dead code, clones, coupling, and a health score.
English | 日本語 | 简体中文 | Français
Code quality analysis for Python in the age of AI coding.
Building with Cursor, Claude, or ChatGPT? pyscn keeps AI-generated code maintainable with structural analysis.
# Run analysis without installation
uvx pyscn@latest analyze .
# or
pipx run pyscn analyze .
One command scores your whole codebase (0-100 with an A-F grade) and generates an HTML report that shows what to fix first.
pyscn looks at your code from five angles:
100,000+ lines/sec • Built with Go + tree-sitter
pyscn is the Python analyzer of polyscan. For JavaScript, TypeScript, Go, Rust and C++, run:
npx polyscan analyze .
Same five angles, same 0-100 score, one HTML report.
Polyscan App files a weekly audit report as a GitHub Issue. Free for public repositories.
pyscn ships Agent Skills that teach AI coding agents when and how to run each analysis: health checks, refactoring, architecture review, and CI-friendly reports.
uvx add-skills ludo-technologies/pyscn
This installs the Skills into your project. They work with Claude Code, Cursor, Codex, Gemini CLI, and many other agents (add --agent cursor etc. to target one, --global for all projects).
Then just ask your agent:
"Analyze the code quality of the app/ directory"
"Find duplicate code and help me refactor it"
"Show me complex code and help me simplify it"
For tighter integration, the bundled pyscn-mcp server exposes the same analyses as MCP tools to Claude Code, Cursor, ChatGPT, and other MCP clients.
Claude Code plugin (sets up the MCP server and the Skills together):
claude plugin marketplace add ludo-technologies/pyscn
claude plugin install pyscn-mcp@pyscn-marketplace
Manual setup for Claude Code:
claude mcp add pyscn-mcp uvx -- pyscn-mcp
Cursor / Claude Desktop: add to your MCP settings (~/.config/claude-desktop/config.json or Cursor settings):
{
"mcpServers": {
"pyscn-mcp": {
"command": "uvx",
"args": ["pyscn-mcp"],
"env": {
"PYSCN_CONFIG": "/path/to/.pyscn.toml"
}
}
}
}
Dive deeper in mcp/README.md for setup walkthroughs and docs/MCP_INTEGRATION.md for architecture details.
# Install with pipx (recommended)
pipx install pyscn
# Or with uv
uv tool install pyscn
macOS Intel (x86_64): PyPI wheels are built for Apple Silicon only (the Intel wheel was dropped in v1.5.1), so
uvx,pipx,uv, andpipcannot install pyscn on Intel Macs. Usebrew install pyscnorgo install github.com/ludo-technologies/pyscn/cmd/pyscn@latestinstead.
git clone https://github.com/ludo-technologies/pyscn.git
cd pyscn
make build
go install github.com/ludo-technologies/pyscn/cmd/pyscn@latest
pyscn analyzeRun comprehensive analysis with HTML report
pyscn analyze . # All analyses with HTML report
pyscn analyze --json . # Generate JSON report
pyscn analyze --json --output - . | jq # JSON report on stdout
pyscn analyze --json --html --no-open . # JSON and HTML reports from one run
pyscn analyze --select complexity . # Only complexity analysis
pyscn analyze --select deps . # Only dependency analysis
pyscn analyze --select complexity,deps,deadcode . # Multiple analyses
pyscn analyze --skip-communities . # Skip module community detection
pyscn checkFast CI-friendly quality gate
pyscn check . # Quick pass/fail check
pyscn check --max-complexity 15 . # Custom thresholds
pyscn check --max-cycles 0 . # Only allow 0 cycle dependency
pyscn check --select deps . # Check only for circular dependencies
pyscn check --select di . # Detect DI anti-patterns (opt-in)
pyscn check --allow-circular-deps . # Allow circular dependencies (warning only)
pyscn initCreate configuration file
pyscn init # Generate .pyscn.toml
💡 Run
pyscn --helporpyscn <command> --helpfor complete options
Create a .pyscn.toml file or add [tool.pyscn] to your pyproject.toml:
# .pyscn.toml
[complexity]
max_complexity = 15
[dead_code]
min_severity = "warning"
[output]
directory = "reports"
⚙️ Run
pyscn initto generate a full configuration file with all available options
📖 pyscn documentation site — installation, rule catalog, CLI reference, configuration, output specification
For contributors: Development Guide • Architecture • Testing
For commercial support, custom integrations, or consulting services, contact us at contact@ludo-tech.org
MIT License — see LICENSE
Built with ❤️ using Go and tree-sitter
Source-derived launch command. Check the maintainer’s required arguments and credentials before running:
uvx pyscn-mcpMerge this template into ~/Library/Application Support/Claude/claude_desktop_config.json. Keep existing servers. Add any arguments, credentials, and permissions required by the maintainer; this template has not been install-tested.
{
"mcpServers": {
"io-github-ludo-technologies-pyscn": {
"command": "uvx",
"args": [
"pyscn-mcp"
]
}
}
}Restart Claude Desktop completely for changes to take effect. Confirm the server appears connected in the client’s tool list, then try a read-only example from its documentation.
Claude Desktop setup referencepyscn-mcppypipyscn works with any MCP-compatible client. Copy the config snippet from the Configuration section above and add it to the file shown for your client, then restart the application.
~/Library/Application Support/Claude/claude_desktop_config.jsonRestart Claude Desktop completely for changes to take effect.~/.cursor/mcp.jsonRestart Cursor for changes to take effect..vscode/mcp.jsonReload VS Code window for changes to take effect.~/.codeium/windsurf/mcp_config.jsonRestart Windsurf for changes to take effect..mcp.jsonSave at the project root, then start Claude Code in that project and review the MCP server approval prompt. Keep real credentials out of shared files.