Claude MarketplacesSubmit

QA Radar

muratkus/qaradar

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.

tools: 7
transport: STDIO
last updated: Apr 23, 2026

Tools

7 tools

Public tool metadata for what this MCP can expose to an agent.

qaradar_healthcheckFull quality overview of a repository

Full quality overview of a repository

No parameter schema in public metadata yet.

qaradar_risky_modulesWhat to test first; which files are riskiest

What to test first; which files are riskiest

No parameter schema in public metadata yet.

qaradar_churnHotspot detection; where regressions tend to occur

Hotspot detection; where regressions tend to occur

No parameter schema in public metadata yet.

qaradar_coverage_gapsFiles with low coverage; where the blind spots are

Files with low coverage; where the blind spots are

No parameter schema in public metadata yet.

qaradar_untested_filesSource files with no corresponding test files

Source files with no corresponding test files

No parameter schema in public metadata yet.

qaradar_pr_riskWhich changed files in this PR need attention

Which changed files in this PR need attention

No parameter schema in public metadata yet.

qaradar_should_runAfter finishing work: should QA Radar re-analyze, and over the diff or the whole repo?

After finishing work: should QA Radar re-analyze, and over the diff or the whole repo?

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly

Agent CaffeineSponsoredClose your lid, come back to finished work

SnugSponsoredThe clipboard manager for the AI era Promote your product hereReach 125k+ visitors monthly

WaxSponsoredBlock anything with supervision, without erasing your iPhone Promote your product hereReach 125k+ visitors monthly

knobsSponsoredSee your site on any phone, any day, in any language

Readme

QA Radar

Give your AI coding agent the quality brain it doesn't have to grow from scratch.

QA Radar analyzes your codebase and produces a structured quality health report — combining git churn, test coverage, and test-to-source mapping into risk-scored modules. It works as an MCP server for AI coding agents (Claude Code, Cursor, Windsurf) and as a standalone CLI for humans and CI pipelines.

Built for developers who want their AI agent to write targeted tests, not generic ones.

Quick Start

Claude Code — one step:

/plugin marketplace add Muratkus/qaradar
/plugin install qaradar@qaradar-marketplace

Then ask your agent: "What should I test first?"

Or run directly without installing:

uvx qaradar serve

Full install options ↓

What It Does

QA Radar answers the question every new team member (and every AI agent) asks: "What should I test first?"

It scans three signals and combines them into a per-file risk score:

View the full README on GitHub

Details

Repository: github.com/muratkus/qaradar
Package: qaradar
Transport: STDIO
Registry: MCP registry, active