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

Server implementation of the Model Context Protocol (MCP). Currently allows tools to be exposed to LLMs supporting the protocol.

Context Limiter & Output Vetter for context bloat. It is a highly specialized, structure-aware JSON built specifically to intercept and compress MCP responses before they annihilate your LLM's...

MCPC is the SDK for building agentic MCP (Model Context Protocol) Servers. You can use it to:

A Model Context Protocol (MCP) server implementation for the Gmail API, providing a standardized interface for email management, sending, and retrieval.

DockaShell is an MCP server that gives AI agents isolated Docker containers to work in. MCP tools for shell access, file operations, and full audit trail.

A powerful LinkedIn profile analyzer MCP (Model Context Protocol) server that interacts with LinkedIn's API to fetch, analyze, and manage LinkedIn posts data.

Convert any MCP server into a Claude Skill with 90% context savings.

Ultra-fast semantic tool filtering for MCP (Model Context Protocol) servers using embedding similarity. Reduce your tool context from 1000+ tools down to the most relevant 10-20 tools in under 10ms.

is now fully supported and can be used directly from GASADK (Google Apps Script Agent Development Kit).

A Unified MCP Server Management App (MCP Manager).

A Model Context Protocol (MCP) server that provides access to WolframAlpha's LLM API. https://products.wolframalpha.com/llm-api/documentation

Manage Tampermonkey userscripts via Model Context Protocol (MCP). List, read, write, patch, and delete userscripts directly from AI-powered development tools.
Agent Skills

A curated list of delightful NoCode / LowCode applications and resources. For more awesomeness, check out awesome.

Codex Skill for producing authorized digital-human talking-head videos with MiniMax overseas voice cloning and HeyGen Image-to-Video.

https://github.com/user-attachments/assets/023c0a9c-194a-45a9-bb88-ac8f16f5ffd5

本项目围绕吴恩达老师在 DeepLearning.AI 推出的 Agentic AI 系列课程,致力于为中文学习者提供高质量的课程内容翻译、系统化的知识梳理、关键概念解析以及配套示例代码的详细解读。项目不仅帮助学习者跨越语言障碍,更通过结构化整理与实践引导,深入理解“智能体”(Agent)在现代 AI 系统中的核心作用,掌握构建自主、协作、推理型 AI 应用的关键方法。
· · · crafted on a 24×24 grid and trusted by 500,000+ developers.

Fast, AI-ready, and zero-config. Free and open source, forever.

A cross-platform desktop app (Tauri + React) for installing, organizing, updating, and syncing Agent Skills to multiple AI coding tools' global or project-level skills directories.

Screenshot testing is key to validate your app's appearance and functionality. It efficiently detects visual issues and tests the app as users would use it, making it easier to spot problems.

zvm (Zig Version Manager) lets you easily install/upgrade between different versions of Zig.

A high-performance Markdown parser and renderer for Angular, React, Svelte, Vue, HTML and ANSI.

Visual skill manager for AI agents. Desktop app and TUI.

基于 Vant 设计语言,为小程序与 H5 提供一致、类型安全且高度可定制的开发体验。