Cursor インストールガイド
開発者向け MCP サーバーとよく使われる AI コードエディタ。
MCP Servers
A complete, driver-based RAG (Retrieval-Augmented Generation) pipeline for Laravel. Built on Prism PHP for provider-agnostic LLM and embedding support.
Transparent MCP proxy that reduces the token cost of large upstream tool responses for nearly every other MCP server imaginable.
MCP server for Things 3 via Things Cloud API
Works transparently with , , , and any MCP-compatible agent. Also supports shell command governance and a language-agnostic HTTP API.
Heimdall — MCP server for the Apple App Store Connect API and App Store Server API (StoreKit 2). 890 tools across 13 profiles, generated from Apple's OpenAPI spec, plus one-call macros for worldwide...
Autonomous agents that find your clients on LinkedIn, on a server you own. An MCP server with 26 tools, so Claude or Cursor can run it. Self hosted LinkedIn outreach, AGPL, one command install.
Add vision to text-only models in Opencode (, ) — , no manual file saving.
This is an example of an application that's exclusively accessible via Model Context Protocol (MCP).
MCP server that gives any LLM its own computer — managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents.
Build WordPress sites with your AI
Agent Skills
Collection of Agent Skills for Autodesk Platform Services.
从经典书籍中蒸馏 AI-Agent 可调用的 Skills，让知识从“读过”变成“遇到问题时能用”。
Control Home Assistant smart home and query states using MCP protocol.
Agent skills
Agent skills for OpenCode. Install with npx skills or clone directly.
AI assistant for Obsidian with , , and powered by Google Gemini.
Agent skills that give AI agents live web data — search, scrape, and extract structured data with Extraction Templates and Web Search Agents, plus one-command business intelligence workflows.
A collection of skills for AI coding agents working with Azure Cosmos DB. Skills are packaged instructions and scripts that extend agent capabilities.
- awesome-tests — plan, write, improve, and review behavior-focused automated tests and test strategies. - code-review — perform adaptable generic, scoped, and plan-backed implementation reviews.
Ilya Sutskever的认知操作系统。不是语录合集，是可运行的思维框架。Made with 女娲.skill
AI coding agents can perform security reviews, but they hallucinate framework control numbers, miss entire vulnerability categories, and produce inconsistent output across runs.
一个可复用的 Codex skill，用来做跨市场的“供应链瓶颈 / 需求冲击 / 贝叶斯更新”式投资研究。