About code-health-suite
Code Health Suite is a Python code-quality MCP server for developers and teams. Its standard-library-only analysis covers complexity, security, dependencies, tests, types, and more.
Key features
- 01Analyze complexity and project health scores
- 02Find unused code and code clones
- 03Scan security issues and dependencies
- 04Inspect imports and module coupling
- 05Audit tests, types, environment, and commits
- 06Combine findings in a full health report
Use cases
- 01Review a Python project’s overall code health
- 02Find security and dependency risks
- 03Assess change impact before modifying files
- 04Check test quality and type annotation coverage
MCP support
Exposes 28 MCP tools across 16 analysis engines for MCP clients, including individual audits and a combined health check.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
28Saved tool list · updated 2w ago
| Parameter | Type | Required | Description |
|---|---|---|---|
| top | integer | No | Return only top N functions by complexity. 0 = all. |
| path | string | Yes | File or directory path to analyze. |
| sort_by | enum | No | Sort metric (default: complexity).complexity | cognitive | length | nesting |
| threshold | integer | No | Cyclomatic complexity threshold (default: 10). |
Details
From the project READMECode Health Suite
16 analysis engines, 28 MCP tools for Python code quality. Zero external dependencies.
Quick Start
As MCP Server (Claude Desktop / Claude Code)
{
"mcpServers": {
"code-health": {
"command": "code-health-suite"
}
}
}
Install from PyPI
pip install code-health-suite
Or with uvx (no install needed):
uvx code-health-suite
Install from GitHub
pip install git+https://github.com/nge/code-health-suite
Tools
| # | Tool | Engine | What it does |
|---|---|---|---|
| 1 | analyze_complexity | complexity | Per-function CC, cognitive complexity, nesting, grades |
| 2 | get_complexity_score | complexity | Project health score 0-100 |
| 3 | find_dead_code | dead-code | Unused imports, functions, variables, arguments |
| 4 | security_scan | security | OWASP vulns, CWE-mapped findings |
| 5 | get_security_score | security | Security health score 0-100 |
| 6 | analyze_imports | import-graph | Import dependency graph, circular deps |
| 7 | get_import_health | import-graph | Import architecture score 0-100 |
| 8 | find_clones | clone-detect | Type-1/2/3 code clone detection |
| 9 | analyze_test_quality | test-quality | Test suite metrics, anti-patterns |
| 10 | full_health_check | all engines | Combined report with overall grade |
| 11 | find_hotspots | hotspot | Files with high git churn AND high complexity |
| 12 | get_hotspot_score | hotspot | Project churn-complexity score |
| 13 | audit_dependencies | dep-audit | Outdated/vulnerable dependency check |
| 14 | analyze_change_impact | change-impact | Blast radius of file changes |
| 15 | get_coupling_score | change-impact | Module coupling metrics |
| 16 | analyze_types | type-audit | Type annotation coverage |
| 17 | get_type_score | type-audit | Type coverage score 0-100 |
| 18 | audit_env | env-audit | Environment variable audit |
| 19 | audit_git_commits | git-audit | Commit quality audit (security + complexity) |
| 20 | get_git_audit_score | git-audit | Git commit health score |
Requirements
- Python 3.10+
- Zero external dependencies (stdlib only)
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.