Gives AI coding agents a structured answer to "what should I test first?" by combining git churn, coverage gaps, and test-to-source mapping into per-file risk scores. Exposes six MCP tools including `qaradar_healthcheck` for full repo quality snapshots, `qaradar_risky_modules` for ranked hotspot lists, and `qaradar_pr_risk` for diff-aware scoring of changed files only. Normalizes coverage formats across Python (coverage.py), JavaScript (LCOV), Go (cover profiles), and Java (Cobertura) so agents don't burn tokens parsing `git log --numstat` or wrestling with ecosystem-specific conventions. Works as a Claude Code plugin with slash commands or as a standalone MCP server. Reach for this when you want your agent to write targeted tests instead of guessing which modules are regression magnets.
claude mcp add --transport stdio muratkus-qaradar uvx qaradar