Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers
Zig code intelligence server and MCP toolset for AI agents. Fast tree, outline, symbol, search, read, edit, deps, snapshot, and remote GitHub repo queries.
Damn Vulnerable MCP Server
Build , and workflows with uAgents, ASI:One, Agentverse, MCP, the A2A protocol, LangChain, CrewAI, Gemini, Claude and OpenAI.
n8n custom node for MCP
🚀 The fast, Pythonic way to build MCP servers and clients.
可私有部署的多租户知识智能体平台：统一 RAG、知识图谱、多智能体、MCP/Skills、沙盒与权限管理。Self-hosted knowledge agent platform for RAG, knowledge graphs and multi-agent workflows.
A full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
A framework helps you quickly build AI Native IDE products. MCP Client, supports Model Context Protocol (MCP) tools via MCP server.
LangChain 🔌 MCP
UI over MCP. Create next-gen UI experiences with the protocol and SDK!
Game Boy / Game Boy Color / Super Game Boy emulator, debugger and embedded MCP server for macOS, Windows, Linux, BSD and RetroArch.
A community driven registry service for Model Context Protocol (MCP) servers.
Agent Skills
Internal Safety Collapse in Frontier Large Language Models
Wakaru unpacks webpack, esbuild, and other production bundles, then reverses minifier and transpiler output into readable modern JavaScript.
This skill removes 20+ patterns of AI slop from your writing and it can also help you detect slop as well.
This repository contains skills to use with Claude Code.
Claude Code plugins for power users
简体中文 │ Website │ API Docs │ PYPI SDK │ Deployment Guide
Real time communication for agents. Wake on message, channels, DMs and actions. Useful for orchestrating agents.
🦀 Crabwalk 🦀 Real-time companion monitor for OpenClaw agents.
Open Source AI trading agent that operates autonomously across 1000+ markets - Polymarket, Kalshi, Binance, Hyperliquid, Solana DEXs, 5 EVM chains.
面向 Web 逆向分析与接口签名还原场景的 Skill，围绕 camoufox-reverse MCP 构建单一工作流：先用 Camoufox 反检测浏览器完成网络捕获、源码定位、Hook 调试与反检测验证，再按需落地到 Node.js 或 Python 算法还原与自动化调用。
A lean .claude/ setup for daily development. Seven specialist agents, twelve workflow skills, six modular rules, and eight safety/productivity hooks.
the interactive repo-local install paths (./install.sh and clawhip install from a clone) can offer to star this repo after a successful install when gh is installed and authenticated.