pyscn-mcp

Python Code Quality Analysis with pyscn MCP

Use the pyscn MCP tools for Python code quality analysis.

Available Tools

Tool Selection Guide

Common Parameters

• path (required): Path to Python file or directory
• recursive (analyze_code): Recursively analyze directories (default: true)
• analyses (analyze_code): Array of analyses to run - complexity, dead_code, clone, cbo, deps

Examples

Quick Health Check

Use get_health_score for a quick overview:

• Returns score 0-100 with letter grade (A-F)
• Category breakdowns for maintainability, reliability, etc.

Detailed Analysis

Use analyze_code with specific analyses:

• analyses: ["complexity"] - Only complexity
• analyses: ["clone"] - Only duplicates
• analyses: ["dead_code"] - Only dead code
• analyses: ["complexity", "dead_code"] - Multiple

Complexity Thresholds

Use check_complexity with:

• min_complexity: Minimum to report (default: 1)
• max_complexity: Maximum allowed (default: 0 = no limit)

Clone Detection

Use detect_clones with:

• similarity_threshold: 0.0-1.0 (default: 0.8)
• min_lines: Minimum lines to consider (default: 5)

Always explain results and suggest improvements based on findings.