MCPs + Skills
Stacks
Curated stacks
Frontend Developer
Build interfaces, test in a browser, and work with project data.
View stack →02Research
Find sources, read documents, and organize evidence.
View stack →03Customer Support
Find customer context, consult knowledge, and prepare responses.
View stack →04Backend & APIs
Explore APIs, inspect application data, and investigate service errors.
View stack →05Data Analysis
Query datasets, explore spreadsheets, and communicate findings.
View stack →06DevOps
Inspect infrastructure, follow deployments, and understand system health.
View stack →07QA & Testing
Check user journeys, exercise APIs, and track reproducible defects.
View stack →08Technical Writing
Read source material, check references, and maintain clear documentation.
View stack →09Product Management
Connect customer context, product decisions, and delivery work.
View stack →10SEO & Content
Research topics, inspect pages, and ground content decisions in evidence.
View stack →11Design & Accessibility
Bring design context into implementation and review the rendered experience.
View stack →12Security Review
Review your code, inspect dependency risks, and document remediation work.
View stack →Build my stack
Your stack / Cursor
QA & Testing
4 selected
Account collections save selected external MCPs only. Marketplace subscriptions and skills keep their existing setup paths. Browser-local stacks below remain separate.
Browser checks
Exercise user journeys and inspect browser behavior.
Playwright Model Context Protocol Server - Tool to automate Browsers and APIs in Claude Desktop, Cline, Cursor IDE and More 🔌
7 alternatives
MCP server for browser automation using Playwright
AI-assisted Playwright MCP framework for test planning, generation, healing, GitHub traceability, CI/CD, and hallucination detection.
一个功能强大的浏览器自动化技能，基于 Playwright 构建，通过 MCP 协议为 OpenClaw 提供 101 完整的浏览器操作能力。OpenClaw skill for browser automation using Playwright - 101 tools for complete browser control
Playwright MCP fork that works with Cloudflare Browser Rendering
API checks
Inspect service contracts and prepare API test cases.
Postman MCP Server — connect AI agents (Claude Code, Cursor, VS Code Copilot, Gemini CLI) to your Postman collections, OpenAPI specs, and environments via Model Context Protocol (MCP)
7 alternatives
Create, organize, and manage API collections, specifications, and team workspaces
OpenAPI specification MCP server.
MCP Server (Model Context Protocol) for turning OpenAPI specifications into a MCP Resource
Dockerized MCP Server to allow your AI agent to access any API with existing api docs
A tool that converts OpenAPI specifications to MCP server
Allow AI to wade through complex OpenAPIs using Simple Language
Defect tracking
Connect reproducible failures to issues and follow-up work.
MCP server for Atlassian tools (Confluence, Jira)
7 alternatives
Create, search, and manage issues, projects, and team workflows
Manage repositories, users, releases, and automate GitHub workflows
Tools for interacting with the GitHub API, enabling file operations, repository management, searc...
GitHub's official MCP Server
GitHub Actions Model Context Protocol Server
An experimental GitHub MCP server with local database.
网页控制台 + Rust Agent。Cloudflare Worker 主通道，GitHub Issue 备用。MCP接入AI，全自动渗透必备。
Testing skill
Use structured test design and debugging guidance.
Production-grade engineering skills for AI coding agents.
3 alternatives
Marketing skills for Claude Code and AI agents. CRO, copywriting, SEO, analytics, and growth engineering.
Find and investigate frontend regressions through targeted testing.
Check web application behavior with browser-driven tests.