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

MCP server that gives any LLM its own computer — managed Docker workspaces with live browser, terminal, code execution, document skills, and autonomous sub-agents.

is the easiest way to connect any MCP client (like Claude or Cursor) with the browser using browser-use.

Advanced search and retrieval for web crawler data. With , your AI client filters and analyzes web content under your direction or autonomously.

Norman MCP Server Your finances, inside your AI assistant. Norman connects your accounting, invoicing, and VAT filing directly to Claude, Cursor, and any MCP-compatible AI. https://mcp.norman.

Works transparently with , , , and any MCP-compatible agent. Also supports shell command governance and a language-agnostic HTTP API.

Build WordPress sites with your AI

Specialized bridge designed to connect LLMs and AI agents directly to Siemens SIMATIC TIA Portal V21.

Local multi-agent coding orchestrator with 22 pipeline roles, TDD enforcement, SonarQube integration, and automated code review. Supports Claude, Codex, Gemini, OpenCode and Aider.

A complete, driver-based RAG (Retrieval-Augmented Generation) pipeline for Laravel. Built on Prism PHP for provider-agnostic LLM and embedding support.

- — MCP Protocol v2 (spec revision 2026-07-28, streamable HTTP) and experimental StrongDM API support are here — see the release notes.

Give Claude on the (claude.ai) and read/edit access to files and a whitelisted shell on your local machine, over HTTPS via Tailscale Funnel, gated by OAuth 2.1. No desktop app, no device install.

Streamable HTTP MCP server for Claude.ai custom connectors.
Agent Skills

This is the v3.0 rewrite of EasyApi. For the source code of stable v2.x releases, see the stable/v2.x.x branch.

gentle-pi installs in Pi: a senior-architect operating layer for Spec-Driven Development, focused subagents, strict TDD evidence, reviewable work units, safety guards, project/user skill discovery,...

Hold CapsLock or Space + a key. Navigate without leaving home row, dictate by voice, let an LLM drive your computer.

An iterative deep-logic security audit agent for Claude Code. Nemesis combines two complementary audit methodologies in an alternating feedback loop to find bugs that neither can catch alone.

请在 中执行。若提示脚本被禁,先运行:Set-ExecutionPolicy -Scope CurrentUser RemoteSigned

上帝skill

- create-onboarding-video — Build app onboarding videos with Remotion. - react-native-keyboard-handling — Frame-perfect, native-feeling keyboard handling in React Native / Expo (fixes Android 15...

AI Trading Analyst for Claude Code. Run full stock analyses with 5 parallel agents, build investment theses, assess risk, screen for opportunities, analyze options, and produce professional PDF...

LLM agents forget everything between sessions. Context compaction drops critical decisions, cross-session knowledge vanishes, and long conversations push early information out of the window.

这些Skills需要在支持Skills功能的Claude环境中使用,官方教学:https://www.anthropic.com/news/skills

是一个 OpenCode Skill,帮助你将 Markdown 文稿快速转化为可导入 PowerPoint 的 SVG 文件。

139个完整的小红书运营技能 - Claude Code 技能插件系统。覆盖内容创作、账号运营、互动运营、数据分析、电商转化、平台规则、工具生态、营销推广、增长策略9大分类。