AI tool plugins: Testing and quality
Our pass of counted 935 plugins in the category Testing and quality, in 966 listings. 6 appeared in the last 7 days and 0 left in the last 30. The leader by Stars (GitHub) is playwright-mcp, with 38k.
The most popular
Ranked by Stars (GitHub), the figure this marketplace publishes. Figures of different marketplaces are never added up.
-
playwright-mcp io.github.microsoft/playwright-mcp
Playwright Tools for MCP
GitHub stars: 38 027 -
Playwright Pro turns your AI coding agent into a senior test automation engineer. Instead of generating tutorial-quality tests with brittle CSS selectors, Playwright Pro enforces…
GitHub stars: 28 021 -
Teaches AI coding agents to create and maintain promptfoo eval suites. Encodes best practices like deterministic assertions first, file-based test organization, correct…
GitHub stars: 25 902 -
End-to-end API testing — generate and run tests from OpenAPI, curl, Postman, or real user traffic.
GitHub stars: 18 545 -
Open-source browser agent driven via CDP — direct browser control, 79K stars, YC W25. browser-harness gives Claude Code direct, low-level control of a real Chrome browser via the…
GitHub stars: 18 391 -
Stealthy browser automation, testing, and web-scraping via CDP Mode.
GitHub stars: 13 064 -
mobile-mcp io.github.mobile-next/mobile-mcp
MCP server for iOS and Android Mobile Development, Automation and Testing
GitHub stars: 8 998 -
mockserver com.mock-server/mockserver
Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.
GitHub stars: 4 987 -
AI browser agent: browses, clicks, types, and reads real web pages from plain-English instructions.
GitHub stars: 2 744 -
Enforces Test-Driven Development by intercepting file operations in Claude Code. When Claude attempts to edit or write files, TDD Guard validates the changes against TDD…
GitHub stars: 2 360 -
Skills and interactive Copilot canvas for designing, configuring, testing and deploying agents to Microsoft Foundry.
GitHub stars: 2 053 -
testkube-mcp io.github.kubeshop/testkube-mcp
MCP server for Testkube - Manage test workflows, executions, and artifacts via AI assistants
GitHub stars: 1 665 -
Connect AI coding agents to MATLAB. Run code, tests, and analysis via MCP.
GitHub stars: 1 645 -
A structured software development toolkit that helps Claude Code follow senior-engineer workflows. AI DevKit provides phase-based development lifecycle (requirements, design…
GitHub stars: 1 644 -
Code quality diagnosis using principles from six classic software engineering books (The Mythical Man-Month, Clean Code, A Philosophy of Software Design, Working Effectively with…
GitHub stars: 1 514 -
Render markdown into email-safe HTML, lint drafts for deliverability problems, and preview emails.
GitHub stars: 1 380 -
stdio MCP server for StyleKit styles, templates, assets, tokens, recipes, and lint checks.
GitHub stars: 596 -
Agents and skills for WinUI 3 app development. Create new WinUI 3 desktop apps, convert from other frameworks (WPF, WinForms, Electron, Tauri, Flutter) to WinUI 3, or add features…
GitHub stars: 468 -
Lint agent configurations before they silently fail. 414 validation rules across Claude Code, Codex CLI, OpenCode, Cursor, GitHub Copilot, Gemini CLI, Cline, Windsurf, Roo Code…
GitHub stars: 446 -
flutter-skill io.github.ai-dashboad/flutter-skill
AI-powered E2E testing for 10 platforms. 253 MCP tools. Zero test code needed.
GitHub stars: 388
New in the last 30 days
-
Lab results for phthalates and bisphenols in consumer products, plus crowdfunded testing.
-
Create, test and break real Proxmox VE clusters in QEMU/KVM on the local host.
-
coso-mcp io.github.simonmak-ascent/coso-mcp
Open COSO internal-control review MCP: scope, risk, controls, sampling, testing, workpapers.
-
Load-test a URL, ping it by phase, ramp to find the capacity, compare runs: JSON reports, guardrails
-
Independent checks of paid x402 data sellers and of AI-agent access to shopping and travel sites
-
Lints a phone voice agent prompt and platform config before real callers reach it.
What these plugins usually run and ask for
- Run on a remote server
- 34% Share of plugins with a remote endpoint: the AI tool talks to a server on the internet.
- Run on your machine
- 51% Share of plugins the AI tool starts locally, as a package or a local command.
- Median secrets asked for
- 0.0 Half of the plugins here ask for this many secret settings (API keys, tokens) or fewer, as their marketplaces declare them.
- Bundles with hooks
- 27% Share of plugin bundles that run shell hooks on events of the AI tool.
Counted over the live plugins of this page. Shares and medians are stated only for groups of at least 20 plugins; they describe declarations, not a security review.
Where they are published
How many of these plugins each marketplace lists. One plugin can be on several of them, so the lines do not add up to the total.
Rows come from our latest passes over the marketplaces. A plugin listed on several marketplaces is one row, with the figure of the marketplace the list is ranked by. GitHub figures rank a plugin only when its repository holds no other plugin we track; the figure of a shared repository is shown as the whole repository's and does not rank.
All AI tool plugins · AI tool plugin statistics
Data comes from the public marketplace file https://github.com/github/awesome-copilot/blob/HEAD/.github/plugin/marketplace.json. Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-community/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the public marketplace file https://github.com/anthropics/claude-plugins-official/blob/HEAD/.claude-plugin/marketplace.json. Data comes from public marketplace files in GitHub repositories of their authors. Data comes from the public marketplace file https://github.com/github/copilot-plugins/blob/HEAD/.github/plugin/marketplace.json. Data comes from the public marketplace file https://github.com/cursor/plugins/blob/HEAD/.cursor-plugin/marketplace.json. Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Data comes from the public marketplace file https://github.com/anthropics/knowledge-work-plugins/blob/HEAD/.claude-plugin/marketplace.json. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Data comes from the public marketplace file https://github.com/openai/plugins/blob/HEAD/.agents/plugins/marketplace.json. . We publish no contact details for plugin publishers.
Where the data comes from: how the catalog is built