Python code analysis for AI agents: complexity, dead code, clones, coupling, and a health score.
io.github.ludo-technologies/pyscn — Model Context Protocol (MCP) Server
This MCP server performs Python code analysis for AI agents. It focuses on metrics such as complexity, dead code detection, code clones, coupling, and produces a health score. The server’s purpose is described as providing these analysis results for downstream agent workflows.
🛠️ Key Features
Python code analysis for AI agents
Complexity metrics
Dead code detection
Code clone detection
Coupling measurement
Health score
🚀 Use Cases
Assessing Python code complexity for AI-driven evaluation
Identifying dead code in Python projects
Detecting code clones as part of refactoring guidance
Measuring coupling to understand maintainability
Generating a health score for codebase condition tracking
⚡ Developer Benefits
Centralized analysis for AI agents
Actionable software quality signals: complexity, dead code, clones, coupling, health score
⚠️ Limitations
Limited to the analysis areas explicitly described: complexity, dead code, clones, coupling, and health scoring
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:
🧹 Dead code - unreachable code you can safely delete
📋 Duplicate code - copy-pasted and structurally similar code worth merging (Type 1-4 clone detection)
🌀 Complexity - functions that are hard to read and test (cyclomatic and cognitive complexity)
🔥 Module and directory hotspots - per-file quality and per-directory complexity rollups for prioritizing refactors
🏗️ Architecture - circular imports, layer rule violations (clean / layered / hexagonal / MVC presets), and auto-detected module communities that reveal how your code is actually structured
🧩 Class design - classes that do too much or depend on too much (CBO coupling, LCOM4 cohesion)
100,000+ lines/sec • Built with Go + tree-sitter
AI Agent Integration
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.
Agent Skills (Recommended)
bash
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"
MCP Server (Optional)
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):
bash
claude plugin marketplace add ludo-technologies/pyscn
claude plugin install pyscn-mcp@pyscn-marketplace
Manual setup for Claude Code:
bash
claude mcp add pyscn-mcp uvx -- pyscn-mcp
Cursor / Claude Desktop: add to your MCP settings (~/.config/claude-desktop/config.json or Cursor settings):
Path to a .pyscn.toml configuration file. Defaults to the usual config discovery (.pyscn.toml, then pyproject.toml) starting from the analyzed directory.