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
Battle-tested Odoo knowledge for AI agents, validated against real Odoo v17 instances in CI.
An MCP server that connects to a Swagger specification and helps an AI to build all the required models to generate a MCP server for that service.
mori MCP server — a governed memory layer for AI coding agents.
English Français Deutsch Español 日本語 한국어 繁體中文 简体中文
Fictional concept interface—not an actual Codex UI or a measured context, token, speed, or latency benchmark.
Intercept AI requests, track usage, inject MCP tools centrally
MD2Card Markdown 转知识卡片 将 Markdown 文档转换为精美的知识卡片，支持多种风格
A modular MCP server providing AI-driven vulnerability management skills, including severity classification and automated insights.
Shared MCP server for the Upvote.club Public API.
A MetaTrader 5 research toolkit with 90+ AI tools for forecasting, regime detection, pattern recognition, and live trading.
This repository contains a complete tutorial on how to create an MCP (Modular Computational Platform) client in Python using FastAPI.
Easy install scripts and user guide for Zotero MCP — connects your Zotero library to Claude and other AI assistants
Agent Skills
Keep AI slop out of your prose and your repo.
面向 NSFC、NSSFC、各类省部级自科、社科申请书的 AI 写作技能集。从近 20 本成功申请书（管理口）中提炼写作范式，覆盖从研究设计、技术路线、立项依据到文献综述等核心撰写环节。
cursorkleosr Workflow memory system — one local skill plus root markdown state. Keep project context and live task state between agent sessions.
A minimal implementation of Recursive Language Models (RLM) using Claude Code as the scaffold. Implemented by Brainqub3.
两年，我从「前端学习中」变身「AI Full-Stack Developer + Apache Committer + 字节跳动核心项目 Maintainer」。 我没有走任何捷径——我只是重新定义了什么叫「走」。 现在，你也可以。
A collection of cybersecurity skills for AI coding agents. The AI does the heavy lifting; you bring the context about your stack and your priorities.
주요정보통신기반시설(CII) 취약점 분석평가, AI 보안 평가, 로봇 보안 점검, 우주 보안 점검, 시큐어코딩 가이드, 제로트러스트 보안 평가, SW 공급망 보안(SBOM)을 위한 Claude Code 스킬 플러그인입니다.
MCP Fusion is a TypeScript framework that enforces security at the architectural level of every MCP server. Raw data never reaches the LLM without passing through a typed egress firewall.
AI defaults to the mean. Models are trained on millions of average websites. If you don't constrain them, they will build an average website.
A lightweight .NET AI SDK for provider routing, streaming, tool calling, and chat session management.
One-page team capacity: load, buffer, explicit cuts — honest ranges.
Per-task rubric-blind skills for the Parthenon self-evolving legal-agent framework (Harvey LAB).