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
一个功能强大的 Model Context Protocol (MCP) 服务器，基于 TypeScript 和 node-pty 实现持久化终端会话管理。即使客户端断开连接，终端命令也会继续运行，特别适合 Claude、Cursor、Cline 等 AI 助手执行长时间任务。 油管视频地址：https://youtu.be/nfLi1IZxhJs b站视频地址：https://www.
A Go implementation of the OData to Model Context Protocol (MCP) bridge, providing universal access to OData services through MCP tools.
Implementation of the paper: MCP4EDA: LLM-Powered Model Context Protocol RTL-to-GDSII Automation with Backend Aware Synthesis Optimization
mcptools implements the Model Context Protocol in R. There are two sides to mcptools:
This is a server that lets your LLMs (like Claude) talk directly to your BigQuery data — . Think of it as a friendly translator that sits between your AI assistant and your database, making sure they...
A Model Context Protocol (MCP) server for querying the Shodan API and Shodan CVEDB. This server provides comprehensive access to Shodan's network intelligence and security services, including IP...
Transform any OpenAPI/Swagger definition into a fully-featured server – ready to run locally, inside Claude Desktop, or in the cloud.
This MCP server is made for study purposes with use of reverse engineered Rohlik API. It is for personal use only.
ReActMCP Web Search is an MCP (Model Context Protocol) server that integrates web search capabilities into your AI assistant framework.
O único servidor MCP com suporte nativo a NF-e, NFS-e, SPED, eSocial, Simples Nacional e Reforma Tributária 2026 (IBS/CBS) - sem conta, sem chave e sem configuração.
The minimum-overhead way to add AI commands to CesiumJS
The Okta Open Source MCP Server integrates with LLMs and AI agents, allowing you to perform various Okta management operations using natural language and is Generally Available (GA).
Agent Skills
Fetch WeChat Official Account articles and convert them to clean Markdown.
AI Agent Skills for LibLib.tv — 让你的 AI Agent 轻松调用 LibTV 的生图、生视频等 AIGC 能力。
The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all Agent Skill / Claude Code...
Generative AI can make mistakes. You should consider reviewing all output and costs generated by your chosen AI model and agentic coding assistant. See AWS Responsible AI Policy.
A curated collection of reusable Agent Skills for Warp AI agents and Oz.
Welcome to , a repository of specialized "brains" for your AI coding assistants. This project provides a suite of designed to supercharge GitHub Copilot, Claude, Google Gemini, Cursor and other...
You wrote a good SKILL.md. But did the agent actually follow it, or skip the late safety rule, grab an undeclared tool, and report "done" with no proof?
把中文故事文案或一组有序的手绘图片,转换成 3:4 竖屏**:手写体字幕、从左到右的「文字 → 黑白画稿 → 彩色插画」揭示、可选的右下角卷页翻书转场、安全不裁剪的画面构图。基于 Remotion,默认输出无配音、无音乐的 H.264 画面轨,方便后期配音。
— Anthropic Labs' AI design workspace. DESIGN.md files grouped by aesthetic family, remix recipes, prompt packs with example outputs, skills, video teardowns, and launch-week community signal.
本仓库是基于 WorkBuddy / Claude Code / Cursor 等 AI Agent 的**。每个 Skill 是一个自包含文件夹，包含 SKILL.md（Agent 执行指令）、README.md（人类文档）、references/（Prompt 参考）和 assets/（模板 HTML）。
鲁班 | Luban — 把'能用的Skill'打磨成'能被装、能传播、能验证、能进化'的公共资产。Agent skill-polishing workshop: 验料·访行·过尺·慢刨·回炉
你只想说一句“帮我做个 App”，但 Codex 真正需要的是一个能执行、能验证、知道边界、知道何时停下来的目标。 qiaomu-goal-meta-skill turns vague work into a copy-ready Codex /goal command with defaults, verification, boundaries, and pause conditions.