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

A lightweight way to use environment variables in your Cursor MCP server definitions.

Local-first memory layer for CLI agents. Indexes Claude Code, Codex CLI, and Cursor session histories into SQLite + FTS5 — searchable from a CLI, TUI, or MCP server so your next agent session can...

A powerful command-line tool and MCP server for managing Markdown-Driven Task Management (MDTM) files.

MCP server implementation for using Claude API with Claude Desktop, providing advanced API integration and conversation management.

AI-powered penetration testing MCP server

Official Claude in Chrome gives you 58 blocked domains and two browsers. Open Claude in Chrome gives you the whole web. Clean-room reimplementation of Anthropic's browser extension. No blocklist.

Desktop Extensions: One-click local MCP server installation in desktop apps

Desktop extension (.mcpb) for Claude Desktop. Single-click install via Settings → Extensions.

A powerful Clojure-based MCP server built for querying DataScript and integrating with AI workflows.

A simple NextJS MCP client with sensible keybindings

Add vision to text-only models in Opencode (, ) — , no manual file saving.

个人知识库 MCP 服务器 — 对本地文档建立索引,并提供一组飞书 API 工具,通过 MCP 协议供 AI 客户端访问。
Agent Skills

The GEP-powered self-evolving engine for AI agents. Auditable evolution with Genes, Capsules, and Events. | evomap.ai

Unofficial TypeSafe Jev showcase — System One decisions, not chat.

Verified Codex-to-ChatGPT Web reasoning handoffs with local edits, tests, and receipts.

Agentic AI security scanner that hunts exploitable vulnerabilities like an adversary, proves them with executable PoCs, and fixes them test-first.

Penetration Flow Skill 是一个面向 Codex / AI 智能体的开源技能项目,用于本地沙盒、CTF、训练靶场、自有代码审计、授权安全评估和逆向分析流程。

WeChat CLI tool

Reusable Codex skill for building and validating DeepSeek Harness and Cordis plugins

灵眸:电赛-视觉skill

Cross-disciplinary, source-grounded paper deep-reading Agent Skill with vision/text-only routes, domain lenses, and evidence audits.

Agent-agnostic record & replay skill: watch a user demonstrate a workflow (browser via Playwright, desktop via OpenAdapt) and turn it into a reusable AI-agent skill.

Open-source brand skills that turn an idea into a real brand — name, identity, voice & brand book — without leaving your AI agent. Works in Claude Code, Cursor & 70+ agents.

An index of Claude and agent skills for academic work, from literature search to peer review. Organized by where each skill fits in the research lifecycle; each entry notes its license and what it...