Skip to content
Agentmart
Submit a tool

QA Radar

Tells AI agents which files to test first — churn, coverage, and test mapping as risk scores.

Connector by MuratKus · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)
Write a review

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/muratkus-qaradar

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Tells AI agents which files to test first — churn, coverage, and test mapping as risk scores.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
7 read · 0 write · 0 deleteRead-only
Secrets
None asked for
Install scripts
Not scanned yet
Runs as
Python package

Tools by what they do 7

Read from the source code; the running server may list different tools.

Read 7 · Look things up without changing anything.

  • qaradar_churn
  • qaradar_coverage_gaps
  • qaradar_healthcheck
  • qaradar_pr_risk
  • qaradar_risky_modules
  • qaradar_should_run
  • qaradar_untested_files

Tools (7)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • qaradar_churnAnalyze Code Churnread-only

    Use when the user asks which files change most often, what the hotspots are, or where regressions tend to occur. Analyzes git history to find frequently changed files — high-churn files are more likely to contain regressions and deserve stronger test coverage.

  • qaradar_coverage_gapsFind Coverage Gapsread-only

    Use when the user asks which files have low coverage, where the blind spots are, or wants to improve test coverage. Parses coverage reports (coverage.py JSON/XML, Cobertura, LCOV, Go cover profile) and returns files sorted by coverage ascending — worst-covered files first.

  • qaradar_healthcheckQA Health Checkread-only

    Use when the user wants a full quality overview or asks 'what's the health of this repo?'. Analyzes git churn, coverage data, and test mapping to produce a comprehensive quality landscape report with risk-scored modules. Returns a JSON report with: summary stats, risky modules ranked by risk score, untested files, high-churn files, and coverage gaps.

  • qaradar_pr_riskPR Diff Risk Analysisread-only

    Use when the user asks what's risky in this PR, which changed files need review, or which of my changes lack tests. Scores only files changed between a base ref and HEAD — not the whole repo. Uses full-repo normalization so risk scores stay calibrated even when only a few files changed. Automatically detects the base branch from git or GITHUB_BASE_REF if base_ref is not specified. Returns a JSON report with: risky changed files ranked by risk score, changed files without tests, test files touched, and a headline summary.

  • qaradar_risky_modulesFind Risky Modulesread-only

    Use when the user asks what to test first, which files are riskiest, or where regressions are likely. Combines churn frequency, coverage gaps, and missing tests to identify files that deserve the most testing attention. Ranks results by risk score so the most critical files appear first.

  • qaradar_should_runShould QA Radar Re-Run?read-only

    Use after you finish work to decide whether QA Radar should re-analyze the repo. Compares the last recorded run (.qaradar/state.json) against the current git state and the configured cadence ([schedule] in qaradar.toml: interval_days, min_changed_files). Returns a JSON decision: whether to run, the recommended scope ('full' or 'diff'), the reason, and how many commits/files/days have elapsed since the last run. If it returns run=true with scope='diff', follow up with qaradar_pr_risk; if scope='full', follow up with qaradar_healthcheck.

  • qaradar_untested_filesFind Untested Filesread-only

    Use when the user asks which files have no tests, what's completely uncovered, or wants to find testing blind spots. Detects source files with no corresponding test files using naming conventions across Python, JS/TS, Go, Java, Kotlin, Ruby, Swift, and Rust.

Signals

Stars
0
Forks
0
Open issues
1
Weekly downloads
23
Last commit
Jun 7, 2026 (4 months ago)
Last release
Apr 23, 2026 (6 months ago)
Last package publish
Apr 23, 2026 (6 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name
io.github.MuratKus/qaradar
Version
0.3.5
Auth
No auth
Packages
pypi qaradar
License
MIT
Repository
github.com/Muratkus/qaradar
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
Official MCP Registrygithub-graphql
Cite this page

QA Radar MCP server. Agent Mart. https://agentmart.dev/connectors/muratkus-qaradar (last updated 2026-10-24)