mcp-test-runner is an MCP server that lets your AI client (Claude /
Cursor / Codex / Gemini) drive your entire QA loop end-to-end:
* Run tests across pytest / Jest / Cypress / Go / Maestro — single
MCP surface, one env var to switch
* Analyze a URL (Web DOM probe) or a live mobile screen (Maestro
hierarchy) to extract testable modules + candidate cases
* Generate runna
AI-powered characterization test generator that reads Python functions or class methods, synthesizes inputs, captures behavior in a sandbox, and emits pytest files to lock legacy code behavior for safe refactoring.
Agentic code-quality CLI and stdio MCP server that runs real Python and JS/TS quality engines (Ruff, pytest, ESLint, Prettier, Vitest, etc.) for linting, testing, and reviewing code.
Enables AI coding agents to debug Python projects by running pytest, extracting failure locations, displaying code context around failures, and optionally requesting fix suggestions from Gemini.