QA Radar

Overview

QA Radar is a Model Context Protocol server that helps AI agents prioritize which files to test first by calculating risk scores based on code churn, test coverage, and test mapping. Any MCP-compatible AI assistant can call QA Radar's tools directly, letting the model decide when and how to use them during conversations or agent runs.

It runs locally as a Python package installed via uvx qaradar, communicating over stdio without requiring any credentials or external authentication. The current release is v0.3.5, published under the MIT license with source code available at Muratkus/qaradar on GitHub.

QA Radar is listed under AI & Agents and works with any MCP client including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed, and others in the ecosystem. If you maintain QA Radar, you can claim this listing to verify ownership and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "qa_radar": {
      "command": "uvx",
      "args": [
        "qaradar"
      ]
    }
  }
}