Cursor 安装指南
常与开发类 MCP Server 搭配使用的 AI 代码编辑器。
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
16 reusable skills and 6 agents for Codex, Claude Code, Cursor, OpenCode and Grok Bot: Humanizer, ML debugging, PR review and Skill Watch.
is a framework that dramatically improves LLM code agent output quality through structured pre-configuration.
48 agents · 35 frameworks · Research-first, AI-native, depth to the Mariana Trench · Solo founder Day 0 → IPO → public company
Opinionated, interactive health audit for a codebase. The skill scans the repo, forces a scope decision up front, then walks architecture, code quality, tests, performance, and dependencies.
Claude Code skill for recursive research up to PhD level across any domain. Source tiering, WDM + Munger inversion for autonomous decisions, and disk checkpointing to survive context compaction.
minimalist/toy terminal agent harness written in bash
GitHub Knowledge Base Manager - A Claude Code skill for managing local GitHub projects
Your AI Platform Engineer. Self-hosted cloud built for AI agents — deploy, monitor, and operate your infrastructure through natural language. One VPS. One command.
Ultracode Codex plugin
Turn a (a URL from api.anthropic.com/v1/design/h/... or a local .tar.gz) into a written directly into your active Xcode workspace — built, previewed, and visually diff'd against the prototype until...
Sprint planning agenda: capacity, ready backlog, commit bar — no overfill.
Playable 3D previz for AI video. Stage environments, act with keyboard controls (WASD), cut dynamic cameras, and feed exact motion into generative video models.