pyscn MCP Server
io.github.ludo-technologies/pyscn
Python code quality analyzer: complexity, dead code, clones, coupling, and health scoring for AI agents.
What is the pyscn MCP server?
The pyscn MCP server is a Python code quality analyzer that performs structural analysis on codebases to measure complexity, detect dead code, identify code clones, analyze dependencies, and generate a health score (0-100 with A-F grade). It integrates with Claude, Cursor, and other AI agents via MCP tools to help maintain code quality during development.
pyscn analyzes Python codebases from five angles: dead code detection, duplicate code (Type 1-4 clone detection), cyclomatic and cognitive complexity, module/directory hotspots, architecture issues (circular imports, layer violations), and class design metrics (coupling and cohesion). It processes 100,000+ lines per second and generates HTML reports with actionable insights. Use it to identify refactoring priorities, catch architectural problems, and maintain code health in projects built with Cursor, Claude, or ChatGPT.
How to install pyscn
Copy-paste configuration for popular MCP clients.
PYSCN_CONFIGPath to a .pyscn.toml configuration file. Defaults to the usual config discovery (.pyscn.toml, then pyproject.toml) starting from the analyzed directory.
Tools & capabilities
Tools this server exposes to the agent.
analyze— Run comprehensive code quality analysis with HTML or JSON report output, optionally selecting specific analyses (complexity, dead code, clones, dependencies, architecture, class design)check— Fast CI-friendly quality gate that performs pass/fail checks with configurable thresholds for complexity, cycles, and other metricsinit— Generate a .pyscn.toml configuration file for customizing analysis rules and output settings
Use cases
- Identify and refactor complex functions that are hard to test and maintain
- Detect and merge duplicate code patterns across your codebase
- Find dead code and unreachable statements to safely delete
- Analyze circular dependencies and architectural violations in module structure
- Generate automated code quality reports for CI/CD pipelines and pull request reviews
pyscn MCP server FAQ
pyscn is a Python code quality analyzer that scores your codebase (0-100 with A-F grade) and detects dead code, duplicates, complexity, coupling, and architectural issues. It integrates with AI agents like Claude and Cursor via MCP.
Yes, pyscn is open-source under the MIT License. Installation is free via pipx, uv, or PyPI (pyscn-mcp for the MCP server).
For Cursor/Claude Desktop, add to ~/.config/claude-desktop/config.json: {"mcpServers": {"pyscn-mcp": {"command": "uvx", "args": ["pyscn-mcp"]}}}. For Claude Code, use: claude mcp add pyscn-mcp uvx -- pyscn-mcp
No, pyscn does not require authentication. It runs locally on your codebase.
pyscn is designed for Python. For JavaScript/TypeScript and other languages, see the polyscan project.
Yes, the `pyscn check` command is CI-friendly and provides fast pass/fail quality gates with configurable thresholds for complexity, cycles, and other metrics.
README (reference)
Source of truth, from the repository.
English | 日本語 | 简体中文 | Français
<br> <picture> <source media="(prefers-color-scheme: dark)" srcset="assets/logo.svg"> <source media="(prefers-color-scheme: light)" srcset="assets/logo-light.svg"> <img alt="pyscn" src="assets/logo-light.svg" width="320"> </picture>A code quality analyzer for Python vibe coders.
Building with Cursor, Claude, or ChatGPT? pyscn performs structural analysis to keep your codebase maintainable.
Working with other languages? pyscn is part of polyscan — code quality analyzers for JavaScript/TypeScript and more
</div>Quick Start
# Run analysis without installation
uvx pyscn@latest analyze .
# or
pipx run pyscn analyze .
Demo
<img alt="pyscn analysis report" src="https://raw.githubusercontent.com/ludo-technologies/pyscn/main/assets/demo-report.png" width="720">Features
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)
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):
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.
Installation
# Install with pipx (recommended)
pipx install pyscn
# Or with uv
uv tool install pyscn
<details>
<summary>Alternative installation methods</summary>
Build from source
git clone https://github.com/ludo-technologies/pyscn.git
cd pyscn
make build
Go install
go install github.com/ludo-technologies/pyscn/cmd/pyscn@latest
</details>
Common Commands
pyscn analyze
Run comprehensive analysis with HTML report
pyscn analyze . # All analyses with HTML report
pyscn analyze --json . # Generate JSON report
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 check
Fast 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 init
Create configuration file
pyscn init # Generate .pyscn.toml
💡 Run
pyscn --helporpyscn <command> --helpfor complete options
Configuration
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 Bot (GitHub App)
Pyscn Bot monitors your Python code quality automatically.
Features
- PR Code Review - Automatic code review on every pull request
- Weekly Code Audit - Scans your entire repository and creates issues for architectural problems
Documentation
📖 pyscn documentation site — installation, rule catalog, CLI reference, configuration, output specification
For contributors: Development Guide • Architecture • Testing
Enterprise Support
For commercial support, custom integrations, or consulting services, contact us at contact@ludo-tech.org
License
MIT License — see LICENSE
Built with ❤️ using Go and tree-sitter
Related MCP servers

Obsidian Vault MCP
Local research workflow MCP: Zotero sources → MinerU extraction → Obsidian vault with structured analysis and traceable AI skills.

OmniScholar
Literature, Zotero, PDF, citation, materials, and scientific image tools for research agents.
MCP delegation fallback for AI agents to discover capabilities, knowledge, tools, and collaborators.
View repository →Gerencie cobranças, invoices e atendimentos do RCM da Osigu diretamente do seu agente de IA.
View repository →
PerspectiveGraph
Read-only attack-path tools: reachable routes to sensitive assets, and what a fix would cut.

Maqui Analytics
Marketing analytics for local businesses — Instagram, ads, web traffic, SEO and reviews.

