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

This repository contains a Model Context Protocol (MCP) Python server that allows Claude Desktop to interact with Unreal Engine 5.

agentic-obs: A Model Context Protocol (MCP) server that provides AI assistants with programmatic control over OBS Studio via the OBS WebSocket API.

A Model Context Protocol (MCP) server for serverboy, allowing LLMs to interact with a GameBoy emulator. Your LLM can... - Load ROMS - Press Keys - Look at the Gameboy Screen - skip frames

Multi-agent orchestration via MCP. Persistent memory, inter-agent messaging, goal cascade, context budget pruning. One binary, zero config.

MCP server (Model Context Protocol) providing LLM clients (Claude Desktop, Cursor, Windsurf, etc.) with tools to manage a Remnawave VPN panel.

Drive the Chrome you are already logged into - from your terminal or any AI assistant. Cross-platform, MCP-ready.

MCP server that watches video footage and returns license-safe BGM matches, hook windows, and ffmpeg ducking specs for agents.

This project provides a server implementation based on the Model Context Protocol (MCP) that acts as a wrapper around OpenAI's Image Generation and Editing APIs (see OpenAI documentation).

"The all-seeing MCP Server for macOS system monitoring and control."

The MCP (Model Context Protocol) Server for Binary Ninja

Multi-AI consensus MCP server that queries multiple AI models (OpenAI, Claude, Gemini, custom APIs) in parallel and synthesizes responses to reduce bias and improve accuracy.

A Model Context Protocol (MCP) server that enables Claude to read and manipulate in real-time through a WebSocket bridge to a Figma plugin.
Agent Skills

Agent skill that audits vibe-coded apps for common security vulnerabilities introduced by AI coding assistants

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

The MATLAB Agentic Toolkit brings trusted MATLAB capabilities to AI agents, making engineering and scientific workflows agent-ready.

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.

EvoSkill: Automated Skill Discovery for Coding Agents

橙皮书 (Orange Book) Series · by HuaShu (花叔)

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

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.

简单说,就是跟 Claude 说一句话,它会帮我从每天的新论文里筛一轮,挑出值得看的,再把重点论文读完、写成 Obsidian 笔记。日常不用记一堆命令,基本就是:

This repository provides technical guidance for users and developers using Amazon EC2 instances powered by AWS Graviton processors (including the latest generation Graviton5 processors).

为纯文本模型"看图“设计更好的视觉工具箱和技能,支持多图理解,图片问答,前端UI还原、GUI 自动化等,并可选无缝接入多个主流agent,直接识别粘贴图片| A vision toolkit and skill designed for text-only llms — image Q&A, long-screenshot OCR, frontend UI restoration, and...

The main branch is under active development for . The stable releases are maintained in the v0.x branch. The documentation for Rslib v1 is available at v1.rslib.rs.