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

Unfortunately i published the 1.0 by mistake...this package is currently under heavy development so there will be breaking changes in minors...threat this 1.x as the 0.x of any other package.

Enterprise Governance Layer (Identity, RBAC, Credentials, Auditing, Logging, Tracing) for the Model Context Protocol SDK

The GemCP app is a cross-platform desktop application that creates a seamless chat interface for Google's Gemini AI models with extensible capabilities through a Model Context Protocol (MCP)...

Trusted Model Context Protocol (Trusted MCP)

A TypeScript library that bridges OpenAI's Realtime API with Model Context Protocol (MCP) servers, enabling voice-driven tool execution.

This project demonstrates how to build interactive MCP (Model Context Protocol) widgets that run on Cloudflare Workers and can be embedded in AI chat interfaces like ChatGPT.

Offline Model Context Protocol (MCP) server that serves Godot Engine API documentation from a local doc/ folder.

FastMCP for Google's langextract library

This project implements a small team of coding agents using LangGraph and the Model Context Protocol (MCP). The agents use MCP servers to provide tools and capabilities through a unified gateway.

This is a simple MCP (Model Context Protocol) server that connects to the PokéAPI and exposes tools that an LLM can use to fetch Pokémon data, list popular Pokémon, and build a tournament squad.

An example personal assistant built with Mastra and MCP (Model Context Protocol) that helps with various daily tasks and information management.

Private web search for AI assistants via SearXNG — supports Claude, Cursor, and any MCP client
Agent Skills

A Claude Code / Hermes skill + voice app. You turn on, assistant is not normal assistant. Assistant is . The Eridian. From Andy Weir's Project Hail Mary.

A transferable, software-engineering methodology for AI coding agents —

Sumi — UX/UI design intelligence for Claude Code: 43 skills, 168 references, 37 commands, an anti-slop engine, and an auditable citation trail. Start with /sumi:start.

"你们搞大模型的就是码奸,你们已经害死前端兄弟了,还要害死后端兄弟……" ——某位对未来充满警惕的工程师

一个面试准备 Skill,帮你快速生成一份**的面试准备文档——含公司调研、JD 解读、定制自我介绍、STAR 项目预案、高频问题、反问清单、Gap 清单等 8 个章节。

A penetration testing skill built on Kali Linux for AI agents such as Claude Code, OpenClaw, and Hermes Agent. Currently includes 269 CLI tools across 14 categories.

这是一套专业的 Claude Skills,帮助开发者**源代码,而不只是"看懂"。基于认知科学研究,融合精细询问法、自我解释测试和应用迁移验证,确保深度学习而非产生流畅幻觉。

Robots have been around for years but have never been autonomous — someone has to drive them with a remote, and they've stopped at scripted demos.

21 款 可独立安装的视觉风格 Skill · 在线体验 · 交流群 · 授权说明

TinyScientist: A Lightweight Framework for Building Research Agents

把 skills/resume-master 整个目录复制到全局 skills 目录:

A multi-agent system for automated bioinformatics analysis workflows