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

MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

Unified real-time search MCP server supporting general web search, vertical domain search, parallel batch search, and full-page URL content extraction.

The complete Rust SDK for building coding agents.

Connect an MCP Client that only supports local (stdio) servers to a Remote MCP Server.

Multi-engine MCP server, CLI, and local daemon for agent web search and content retrieval — skill-guided workflows, no API keys.

🚀 Universal SDK for building next-gen MCP servers

The Stitch extension for Gemini CLI enables you to interact with the Stitch MCP (Model Context Protocol) server using natural language commands.

Official Docker MCP registry

Agents and MCP Orchestration with Langchain.js, LlamaIndex.TS, and Microsoft Agent Framework!

MCP server SDK/example implemented entirely in bash — build a Model Context Protocol server with no runtime dependency beyond a POSIX shell.

Open Multi-Agent Canvas, created by CopilotKit is an open-source multi-agent chat interface that lets you manage multiple agents in one dynamic conversation. It's built with Next.

The only browser automation that bypasses anti-bot systems. AI writes network hooks, clones UIs pixel-perfect via simple chat.
Agent Skills

是为 Claude Code、Trae 等 AI 客户端设计的专业代码安全审计 Skill。采用白盒静态分析方法论,通过五阶段标准化审计协议,系统性发现和验证源代码中的安全漏洞。

A Claude Code skill that generates 120fps GPU-accelerated animations using Motion.dev (the successor to Framer Motion).

DNA Memory 把一个 Markdown/Obsidian 目录作为长期记忆真源,把 SQLite 作为可删除、可重建的索引。多个 AI 客户端通过同一个 MCP 服务召回、写入和反馈, 不再各自维护互相冲突的长期记忆副本。

Фреймворк агентной разработки для 1С BSL с применением модульного подхода. Позволяет настроить AI-агентов (Cursor, Claude Code и др.

SD 2.5 Prompt 是一套面向 Seedance 2.5 / SD 2.5 视频生成的实用 Skill。它不依赖冗长术语,用五个部分统一处理产品广告、人物动作、原片反推、多模态参考、音乐节奏和复杂打斗。

A prompt-based pipeline for finding, validating, and proving vulnerabilities using LLM sub-agents — structured to resist false positives.

A Claude Code skill that scans Solidity codebases for security vulnerabilities by referencing 36 unique vulnerability types sourced from smart-contract-vulnerabilities.

Deutsch | Español | français | 日本語 | 한국어 | Português | Русский | 中文

Скилл для AI-агентов: Claude Code, Codex, OpenClaw, Hermes и любых других, читающих SKILL.md. Берёт русский текст после нейросети и убирает всё, по чему его палят: канцелярит, «не просто X, а Y»,...

DSH 插件,在 Web 设置页同时提供「技能」与「MCP」两个管理面板,并随包提供统一终端命令 dsh-panel(skill / mcp 两个子命令族)。

🦞 OpenClaw Security Hardening Skill — Scan, audit, and harden your OpenClaw configuration with guided fixes

Bring Codex, Claude Code, Cursor, Gemini CLI, OpenCode, or your own agent. ContentOS is a workflow and data contract, not a model, vendor, or CLI-specific application.