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

An open-source agent toolkit that auto-syncs SDK versions, docs, and examples—built for seamless integration with LLMs, and AI agents ( MCP compatible).

Mobile app automation and verification for AI coding agents. CLI, MCP server, and typed Node.js API for iOS, Android, HarmonyOS, TV, web, macOS, and Linux.

A template for building MCP servers. Clone it, strip what you don't need, wire your API client, define tools. It's designed to be readable and easy to build on.

A community developed and maintained Model Context Protocol (MCP) server that provides access for large language models to the Nasdaq Data Link. Built for use with MCP-compatible clients.

A comprehensive, asynchronous client for the . It bridges the gap between powerful AI models like Anthropic's Claude and a universe of external tools, local/remote servers, and contextual data...

Local-first and static by default — no agent execution, tool calls, LLM calls, or network access.

An MCP (Model Context Protocol) server implementation that provides access to Obsidian vaults through a local REST API.

将Dify工作流作为Model Context Protocol (MCP)服务器暴露给Claude等AI客户端。

- : BNB Smart Chain (BSC) - : Viem 2.23.11, PancakeSwap SDK 5.8.8 - : TypeScript, Node.js (ESM) - : Model Context Protocol (MCP) SDK 1.4.

An MCP that gives your agent the ability to snap a screenshot of webpages. Useful when you want your agent to check its progress during development.

AI agents recompute the same work. trace-mcp makes them reuse instead. The recomputation → reuse layer for AI systems.

This repository contains a collection of example Model Context Protocol (MCP) servers, each demonstrating different integrations and use cases for the MCP standard.
Agent Skills

A collection of security and utility hooks for Claude Code. Hooks allow you to extend Claude Code's behavior by running custom scripts at key points during execution.

专为 打造的专业渗透测试技能包。覆盖信息收集 → 漏洞发现 → 漏洞利用 → 后渗透 → 免杀全流程。对 Claude 说出目标,自动弹出方向键交互面板,即刻开始实战测试。 💡 仓库里的 CLAUDE.md 是独立提示词文件,不想装 Skill 的话可以直接拿去用,按需自取。

This skill makes an AI agent run error analysis on a dataset. Point it at a JSONL/CSV/JSON file of LLM outputs or traces, and it:

Claude Design on claude.ai is excellent. But it's locked.

把 UI 截图、设计稿或 App 参考图交给 Codex,让它先生成完整效果图,再拆分代码界面与 image2 位图资产,最终交付可打开、可点击、可继续修改的 demo。

A Claude Code skill (and universal SKILL.md) that forces any AI to produce human-sounding text by eliminating statistically detectable AI writing patterns.

A starter kit for running large-scale language migrations with Claude Code: the prompts, templates, and scripts behind the process described in .

打破小爱音箱的封闭生态,灵活接入多种 AI 服务,提供 HTTP API 实现远程控制。

本项目基于唐朝老师的《手把手教你读财报(新准则升级版)》,将书中的财报分析方法论提炼为一套自动化的风险检测工具。通过 Claude Code Skill 实现一键排雷:输入股票代码 → 自动获取数据 → 逐条检查 30 条规则 → 输出风险等级报告。

My collection of custom Claude Code skills for productivity and automation.

一套攒起来的 AI 编程流程文档。我自己平时写项目用的那套方法抽成可复用的 markdown 包。

Personal skill collection for , , and — by @LichAmnesia.