3,866 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.
jrobelia/inventree-plugin-ai-toolkit
Skill Claude CodeCodex needs its repo
Run the InvenTree Plugin AI Toolkit devcontainer and execute a plugin's test-all.sh. Covers Docker setup, postCreateCommand, server startup, and the lint/unit/integration/frontend-build/E2E layers.
MCP server Claude CodeCodexCursor +2
MCP server "playwright" as configured in bluelilyc/aipm. Runs locally from the @modelcontextprotocol/server-playwright npm package.
Plugin Claude Code
Bundles 1 skill, 6 commands, 1 MCP server · 227 tokens together
Patent-pending zero-IPC E2E test runtime for AI agents. Drive a real browser in plain English, enforce the VITRON-EA1 fail-closed safety gate, audit WCAG 2.1 AA and NIST SP 800-53, and export signed evidence packs. Local-first, zero telemetry.
deepakkamboj/playwright-accessibility-mcp-server
MCP server Claude CodeCodexCursor +2
MCP server for running the accessibility tests using Playwright and Axe-core. Runs locally from the playwright-accessibility-mcp-server npm package.
Skill Claude CodeCodex
Use when asked to "run QA", "qa check", "test checklist", or execute QA checklists against a running app via browser automation. Requires the browser-bridge MCP server and Chrome extension.
MCP server Claude CodeCodexCursor +2
MCP server exposing Detox mobile E2E workflows to Claude Code. Runs locally from the detox-mcp npm package.
Plugin Claude Code
Bundles 2 skills, 1 command, 1 agent, 2 hooks, 1 MCP server · 137 tokens together
Tauri desktop app test automation via MCP. Launch, inspect, interact with, and test Tauri v2 apps using accessibility tree snapshots and DOM manipulation.
MCP server Claude CodeCodexCursor +2
MCP server "playwright" as configured in takeru/Kagami. Runs playwright_mcp_claude_code_web/mcp.py with python3. Needs 1 environment variable to run.
MCP server Claude CodeCodexCursor +2
MCP server for iOS Simulator automation — accessibility tree, screenshot, tap/swipe/type, and AI screen perception tools. Runs locally from the app-screen-mcp npm package.
NIHARDUGADE/sentinel-mcp-data-governance-agent
MCP server Claude CodeCodexCursor +2
AI-driven functional testing agent. Point it at a URL; it explores the app, generates a test plan, runs it, and reports findings. Web (Playwright) + visual regression + accessibility (axe-core) + REST API contract tests, all driven by your choice of LLM. Runs locally from the sentinel-agent Python package.
MCP server Claude CodeCodexCursor +2
MCP server for automated Godot 4 game testing — launch, run, capture errors. Runs locally from the godot-test-mcp Python package.
Cursor rule Cursor
A Model Context Protocol (MCP) server for automating Playwright tests.
Skill Claude CodeCodex
A QA workflow for testing software changes and fixing reported bugs through an MCP server. QA means checking that software works as expected before release.
MCP server Claude CodeCodexCursor +2
MCP server for testing Electron applications using Playwright. Runs locally from the @kanishka-namdeo/electron-mcp-server npm package. Needs 2 environment variables to run.
MCP server Claude CodeCodexCursor +2
MCP server "cypress-mcp-server" as configured in guyco6742/cypress-runner-mcp. Runs locally from the cypress-mcp-server npm package.
Skill Codex
Build, run, record, replay, debug, and maintain deterministic terminal, TUI, PTY cassette, and browser-terminal agent regression tests with ptywright. Use when an agent needs to drive CLI/TUI apps, create ptywright scripts, configure ptywright.config., record or replay PTY output, solidify browser terminal agent flows…
Cursor rule Cursor
Auto-run Tell Proof verification after UI-changing edits.
MCP server Claude CodeCodexCursor +2
MCP server for LinkTest — automate Google Play closed testing via AI. Runs locally from the linktest-mcp-server npm package.
MCP server Claude CodeCodexCursor +2
Autonomous browser testing engine & MCP toolset for AI coding agents. Runs locally from the ai-web-tester npm package.
Skill Claude CodeCodex
Use the Hronaut desktop Browser MCP for visible, persistent web workflows in isolated agent workspaces. Use for authenticated browser QA with human handoff, localhost or responsive testing, accessibility and performance diagnosis, or tasks that should survive one agent session while the user watches or takes over.
snapshot-site/snapshot-site-mcp
MCP server Claude CodeCodexCursor +2
Capture screenshots, detect visual regressions between page versions, and analyze with AI. Runs locally from the @snapshot-site/mcp npm package. Needs 1 environment variable to run.
naveenanimation20/locatorlabs-mcp
MCP server Claude CodeCodexCursor +2
MCP server for intelligent Playwright locator generation - Get locators, analyze pages, generate POMs, and run tests. Runs locally from the locatorlabs-mcp npm package.
esinecan/mcp-inspector-as-mcp-server
MCP server Claude CodeCodexCursor +2
A lean MCP server that enables LLMs to inspect and test other MCP servers. Runs locally from the mcp-inspector-as-mcp-server npm package.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 81 tokens together
Cross-platform screenshot capture for agent-based UI testing.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: