Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers

LLM <-- MCP --> CodeQL( AST | CFG | CLI | LSP )

Frontier-grade answers from any mix of models — a local MCP server bringing OpenRouter's Fusion panel architecture to any MCP client. Bring your own keys.

Luvv-MCP 是一个 AI 原生的前端安全分析引擎,接入 Claude Code 后,你说一句"帮我审计这个网站",AI 就能自动完成技术栈识别(1.8 万条规则覆盖 CMS/框架/CDN/中间件)、泄露扫描(阿里云 AK、GitHub Token、Webhook、JWT 等 60+ 类敏感信息)、漏洞审计(XSS、开放重定向、CSRF、IDOR、硬编码密码 6...

Verifiable and free cloud compute for AI agents. webMCP + MCP native. Check out our sandboxed Beta + research in the README

This repository is public, allowing users to pull down the Developing Baseball's Statcast MCP.

Open-source MCP server for MetaTrader 5 backtesting, optimization & analytics — pure Rust

An MCP-capable intelligent RSS feed ingestion and summarization to markdown tool.

זה ממש אבל ממש לא אמסיפי לחילנט

Keryx: The Fullstack TypeScript Framework for MCP and APIs

A unified plugin for developers integrating MCP servers into modern JavaScript build tools, including Webpack, Rollup, Vite, and more.

Official Porkbun MCP server — exposes the Porkbun v3 API as 30 native tools for Claude Desktop, Cursor, and other AI agents. Idempotency-safe writes, full domain lifecycle.

Official Anam AI MCP server for managing AI avatars
Agent Skills

A personal library of Claude Code skills — installable prompt extensions that give Claude Code new capabilities.

From TypeScript Source → Rebuilt in Python with ❤️

一个用于 AI 编程助手的社交媒体发布技能,基于 agent-browser 实现自动化发布内容到各大社交平台。

大多数 AI 翻译生硬、欧化、一眼就能看出是机翻。**专为书籍级长文本设计,核心承诺是**。

📦 本仓库已收录至 openclaw-skills(聚合仓库,包含更多 Skills)。推荐 Star 聚合仓库以获取全部更新。

See the Kocoro product site for the current product demo.

A simple testing framework for bash scripts

Feed your AI something healthier than Markdown. allium-lang.org

把课程材料变成可持续学习、可反馈、可复习、可沉淀的 Obsidian 学习系统。

Skills shared by Canghe for improving daily work efficiency with Claude Code.

CatchMe: Make Your AI Agents Truly Personal

Empirically detect the repetitive defaults a model falls back on, then turn those findings into a reusable instruction file that makes future outputs less generic.