Universal MCP server for running tests across pytest / Jest / Cypress / Go, with built-in DOM analyzer, run history, and a self-improvement coach. Stable since v1.0.0 (2026-06-02) — see Stability…
mcp-test-runner is an MCP project maintained in the kao273183/mcp-test-runner repository. The maintainer describes its purpose as “Universal MCP server for running tests across pytest / Jest / Cypress / Go, with built-in DOM analyzer, run history, and a self-improvement coach. Stable…”. Read the project documentation for the complete scope.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| get_runner_info | Which runner is active + all available ones |
| list_tests | Enumerate tests in the project |
| run_tests | Run tests (filter / headed / browser; last two pytest-playwright only) |
| run_failed | Re-run last failures (pytest --lf) |
| get_test_report | Summary (pass / fail / skipped / duration / flaky-in-run) |
| get_failure_details | Per-failure message + screenshot / trace / video paths |
| generate_test | Test skeleton; with module from analyze_url/analyze_screen, a runnable one (Playwright .py or Maestro .yaml) |
| auto_generate_tests | One-shot: analyze URL → generate one test per discovered module |
| codegen | Launch Playwright codegen (web) / hint to maestro studio (mobile) |
| generate_html_report | Render the latest run as self-contained HTML |
| get_test_history | Last N archived run summaries (for trend / flake debugging) |
| analyze_url | Web: DOM probe → modules + selectors + candidate TCs + API endpoints + layout overflow warnings |
| analyze_screen | Mobile: maestro hierarchy → form / cta / tab_bar modules + candidate TCs (noise-filtered) |
| get_optimization_plan | Three-layer self-improvement coach (suite / MCP / AI strategy) |
| run_api_security_scan | v0.8.0 OWASP API Security Top 10 (2023) rule-based scanner — load an OpenAPI 3.x spec, walk path × method, dispatch 5 in-scope rules (API1 BOLA, API2 Broken… |
| URI | What |
Queries the NIST National Vulnerability Database (NVD) via its API.
Scans projects for security vulnerabilities and automatically updates vulnerable dependencies using Trivy.
Search 1,032 verified smart contract vulnerability findings from Sherlock audits by pattern.
Remote MCP for A2A dependency inspector MCP, structured receipts, audit logs, and reviewer-ready evi
Remote MCP for A2A failure replay MCP, structured receipts, audit logs, and reviewer-ready evidence.
A comprehensive Model Context Protocol (MCP) server for ABP.IO framework with 48+ tools for application development, UI generation, and management