AgentHubAgentHub

Use cases/Cursor essentials

Essential MCP stack for Cursor

Starter stack for Cursor: files, GitHub, docs, browser—an AI coding workflow in minutes.

32,146 resources matched · Page 1 of 670

What is Cursor essentials?

Cursor ships first-class MCP support: paste a JSON block into Settings → MCP or .cursor/mcp.json in your project to connect any server. With AgentHub's 1-click config generator, discovery-to-running takes under a minute.

A solid starter stack covers four needs: Filesystem (project files), GitHub (PRs / issues / diffs), Context7 (fresh framework docs to curb hallucinations), and Playwright (browser verification and E2E).

Every resource listed here includes a Cursor-ready config snippet: open the resource page → Cursor tab → copy the JSON; install commands and auth env vars are provided alongside.

Good for

  • Full-stack dev
  • Open source
  • Learning frameworks
  • Small automation scripts

Not ideal for

  • Chat-only use cases
  • Locked-down corporate desktops
Common stack: Filesystem + GitHub + Context7 + Playwright

Related resources

Browse all →

GitHub

v1.2.4

SkillClawHub18.8k

GitHub API integration with managed OAuth. Access repositories, issues, pull requests, commits, branches, and users. Use this skill when users want to interact with GitHub repositories, manage issues and PRs, search code, or automate workflows. For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway). Calls run through the `maton` CLI with OAuth login, or over raw HTTP with a Maton API key where the CLI cannot be installed. Every call is authenticated as the user's connection and reaches only what that connection's authorization allows, which the provider enforces on every request; the endpoints documented here are the ones this skill uses, and any other endpoint of this app needs the user to ask for it by name. Default to read and list calls, and confirm every write or new connection with the user. This file also documents the three constructs that turn a GitHub connection into automation, in the order they are used: the connection (the first step), a hosted function th

source

Playwright (Automation + MCP + Scraper)

v1.0.4

SkillClawHub42.5k

Automates, tests, and debugs browsers with Playwright: locators, auto-waiting, traces, CI runs, and MCP browser control. Use when a test is flaky, times out, or fails only in CI or headless; when a locator matches multiple elements or the wrong one (strict mode violation); when clicks need force, waits become sleeps, or networkidle never settles; for storageState and login setup, request mocking and HAR replay, uploads and downloads, iframes and shadow DOM, popups and dialogs, screenshot diffs that change per machine, trace and report artifacts, sharding a slow suite, device and permission emulation, accessibility checks, driving a real browser through Playwright MCP, extracting data from JS-rendered pages, or porting a Cypress, Puppeteer, or Selenium suite to Playwright. Not for maintaining an existing Cypress or Puppeteer suite (cypress, puppeteer) or for work a plain HTTP request answers (http).

source

novel-generator 是一个中文爽文小说生成技能。用户只需提供一句话方向(如"写个都市重生爽文"),AI 代理即可自动完善提示词、规划大纲、逐章创作并输出为独立 Markdown 文件。 核心特性: 智能提示词生成:从一句话方向自动补全世界观、人设、冲突、爽点设计 分章节创作:每章 2000-3000 字,层层递进,章章有爽点 记忆系统:通过 .learnings/ 记录角色、地点、情节、世界观,确保故事前后一致 情节图解:关键战斗、人物关系、势力分布自动生成 Mermaid 图 失败记录:穿帮、矛盾、崩塌等问题自动记录,持续优化 多题材支持:都市、修仙、玄幻、重生、系统流、末世、科幻、游戏 兼容 Claude Code、Cursor、OpenAI Codex、GitHub Copilot 等所有支持 Agent Skills 的工具。

v1.0.0

SkillClawHub10.4k

根据用户提供的内容方向自动生成提示词并创作爽文小说。适用场景:(1) 用户提供小说方向/题材/关键词,(2) 需要生成章节连贯的长篇爽文,(3) 需要维护角色、地点、情节的连续性,(4) 需要为关键情节生成图解,(5) 需要记录生成失败场景以优化后续创作。支持都市、修仙、玄幻、重生、系统流等多种题材。

source

FAQ

Project-level or global MCP config in Cursor?

Both work: .cursor/mcp.json is shared with your team via the repo; ~/.cursor/mcp.json applies machine-wide. Keep secrets project-local or in env vars.

Do many MCP servers slow Cursor down?

Each enabled server injects tool definitions into context. Enable per project and disable unused servers to keep context for what matters.

Any Windows vs macOS differences?

Same JSON shape; differences are command paths and env-var quoting (npx vs absolute path). AgentHub resource pages distinguish stdio from remote (streamable-http/SSE) setups.

Setup guides for this scenario

Related scenarios

Essential MCP stack for Cursor - AgentHub