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 repo provides a reference implementation for creating a remote MCP server that supports the Streamable HTTP & SSE Transports, authorized with OAuth based on the MCP specification.

Local-first persistent memory for Claude Code & Codex CLI - Rust CLI, hooks, MCP server, SQLite/SQLCipher, auditable recall for long-running coding work.

This MCP server connects your AI agent to — Google's creative suite for image and video generation. Your agent can:

MCP server for FreeCAD — 32 tools for AI-assisted 3D CAD modeling

furi is an easy to use, CLI & API for MCP management.
Agent Skills

Claude Desktop Chinese Patch (macOS & Windows)

Your AI executive team on Discord. 7 specialized agents — Engineering, Finance, Marketing, DevOps, Legal, Management, Chief of Staff. One-click setup on any free-tier server. Built on Clawdbot.

Machine Learning Engineering Open Book

Skills & reviewer agents for AI-first climate science — built and used by a PhD atmospheric scientist

frame-smith 是一个**,不是渲染器。它读你的 brief、定寄存器、选一个效果引擎、铺节拍时间线、配乐加音效、写出 .tsx 并注册进你的 Remotion Root。真正的渲染由它所依附的视频运行时完成。

recursive-mode is an installable skill package for structured AI-assisted software development.

Spotkit — a Claude Code skill that turns a feature description into minimal, abstract SVG product illustrations that all belong to one design system.

Run one command → open the dashboard → your bot is live. Windows · macOS · Linux · VPS — Docker-powered, auto-installed for you.

Convoke extends BMAD Method AI agents with two types of installable modules: Teams bring new agents for a domain, Skills add new capabilities to existing agents.

一个基于 DeepAgentsJS 的智能助手,参考了OpenClaw的设计理念。具有自主记忆和SKILLS编写/执行能力。

五运六气技能路由包 - AI 自动路由 + 确定性推算引擎 + RAG 知识库 + 自进化经验库 | 32 asset / 2124 条医案 / 53 篇文献 | 支持 Claude Code / Cursor / Codex CLI / Cline / OpenClaw | TCM Yunqi Skills Router - AI auto-routing + deterministic...

Process skills that give a Reasonix coding agent the disciplines of a careful engineer: write the test first, debug from evidence, plan before coding, verify before claiming done.