Skip to main content
Glama
neogeweb3

io.github.neogeweb3/code-health-suite

by neogeweb3
README.md
# Code Health Suite

16 analysis engines, 28 MCP tools for Python code quality. Zero external dependencies.

<!-- mcp-name: io.github.neogeweb3/code-health-suite -->

## Quick Start

### As MCP Server (Claude Desktop / Claude Code)

```json
{
  "mcpServers": {
    "code-health": {
      "command": "code-health-suite"
    }
  }
}
```

### Install from PyPI

```bash
pip install code-health-suite
```

Or with uvx (no install needed):

```bash
uvx code-health-suite
```

### Install from GitHub

```bash
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| 13 | `audit_dependencies` | dep-audit | Outdated/vulnerable dependency check |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

TDQS

A3.6/5.0

Scored across 28 tools

Disambiguation4/5

Most tools are clearly separated by domain and by the detail-vs-score pattern (e.g., security_scan vs. get_security_score). The main ambiguity is between analyze_imports and analyze_coupling, which both report instability and hub-like module metrics, so an agent could pick the wrong one for architecture analysis.

Naming Consistency4/5

The server uses a consistent snake_case verb_noun convention, and the get_*_score tools form a recognizable summary pattern. However, verb choice varies across analyze/find/audit/scan/check/detect, and get_import_health and full_health_check break the get_*_score pattern, creating minor inconsistency.

Tool Count2/5

At 28 tools, the server exceeds the comfortable range and will likely burden agent selection. The high count is understandable given the detail-plus-score pairing across many health dimensions, but it still feels oversized for a single MCP server.

Completeness4/5

The suite covers an impressively broad set of Python code-health domains: complexity, security, imports, clones, tests, types, naming, todos, bugs, docstrings, dependencies, hotspots, env vars, and git history. Minor gaps include no actual test coverage percentage and no aggregate score for dead code or clone analysis.

Maintenance

ActivityInactive
ResponsivenessNo issues