Qaradar MCP Server

QA Radar analyzes your codebase and produces a structured quality health report — combining git churn, test coverage, and test-to-source mapping into

Local serverstdioPython

What is the Qaradar MCP server?

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. That is what the qaradar mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The tools it exposes

The server publishes 8 tools. What each one is for:

  • qaradar_healthcheck — Full quality overview of a repository
  • qaradar_risky_modules — What to test first; which files are riskiest
  • qaradar_churn — Hotspot detection; where regressions tend to occur
  • qaradar_coverage_gaps — Files with low coverage; where the blind spots are
  • qaradar_untested_files — Source files with no corresponding test files
  • qaradar_pr_risk — Which changed files in this PR need attention
  • qaradar_should_run — After finishing work: should QA Radar re-analyze, and over the diff or the whole repo?
  • Setup — Add to your Claude Code MCP config (~/.claude/mcp.json for user-level, or .mcp.json in the project root for project-level):

Getting it running

qaradar on PyPI is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Qaradar's toolset — qaradar_healthcheck, qaradar_risky_modules, qaradar_churn and 5 more — is a fair guide to whether it matches your workflow. It is maintained by muratkus; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
qaradar_healthcheckFull quality overview of a repository
qaradar_risky_modulesWhat to test first; which files are riskiest
qaradar_churnHotspot detection; where regressions tend to occur
qaradar_coverage_gapsFiles with low coverage; where the blind spots are
qaradar_untested_filesSource files with no corresponding test files
qaradar_pr_riskWhich changed files in this PR need attention
qaradar_should_runAfter finishing work: should QA Radar re-analyze, and over the diff or the whole repo?
SetupAdd to your Claude Code MCP config (~/.claude/mcp.json for user-level, or .mcp.json in the project root for project-level):

How to install the Qaradar MCP server

{
  "mcpServers": {
    "qaradar": {
      "command": "uvx",
      "args": ["qaradar", "serve"]
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Qaradar to qaradar healthcheck.
  • Use Qaradar to qaradar risky modules.
  • Use Qaradar to qaradar churn.

Frequently asked questions

It connects Qaradar to MCP-compatible AI assistants such as Claude and Cursor, exposing 8 tools (qaradar_healthcheck, qaradar_risky_modules, qaradar_churn, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Qaradar directly.