Cursor 安装指南
常与开发类 MCP Server 搭配使用的 AI 代码编辑器。
MCP Servers

Flagship Model Context Protocol server for generating Product Requirement Documents (PRDs) from codebase context.

MCP server for Minecraft Development

Model Context Protocol server for KiCad on Mac, Windows, and Linux

A Model Context Protocol (MCP) server that provides a standardized interface for AI assistants to interact with a SurrealDB database.

PubNub MCP Model Context Protocol Server for use in Cursor, Windsurf, Claude Desktop, Claude Code and OpenAI Codex and more!

Enterprise MCP server for SQL Server with 20 tools for schema discovery, data operations, and administration.

Asterisk Model Context Protocol (MCP) server.

Bioinformatic MCP server that wraps the most useful functions of the gget library

MCP server for AvaloniaUI

Model Context Protocol server for GraphQL

mem-agent mcp server

TypeScript MCP server for retrieving YouTube transcripts in Claude Desktop, Cursor, Cline, Codex, and other MCP clients
Agent Skills

Personal Codex skills (drop-in folders under ~/.agents/skills/). Catalog: https://jmerta.github.io/codex-skills/

Agent skills extracted from real work. Each one shipped something first.

Static and dynamic analysis tool for detecting malicious code, suspicious binaries, and privacy violations

PM Skills Marketplace: 100+ agentic skills, commands, and plugins — from discovery to strategy, execution, launch, and growth.

(rhymes with "pad") is a set of skills for AI coding assistants. It reviews what the AI is about to work on — the spec, the plan, the architecture, the code — while you can still change it.

Site · Docs · Live demo · Claude plugin · Docker image

Skills for Real Engineers. Straight from my .agents directory.

A collection of public, open-source skills for builders — by Brian Casel at Builder Methods.

Yuan is a unified destiny-reading skill for Codex, Claude Code, and any Agent Skills–compatible runtime.

同事.skill、老板.skill、前任.skill、自己.skill、永生.skill、女娲.skill……

会话 · 聊天记录 · 搜索 · 联系人 · 群成员 · 群昵称 · 收藏 · 统计 · 导出

One command drops a tested, versioned skill into your agent. No more ad-hoc prompts. The same rigorous steps run every time.