Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
A lightweight, handcrafted implementation of the Model Context Protocol focused on what most users actually need: exposing tools with clean Python type annotations.
Give AI agents or scripts direct control over your parametric design canvas and Rhino rendering tools.
MCP X-Ray is a unified open-source security scanning and penetration testing solution for Model Context Protocol (MCP) servers.
Remote Model Context Protocol (MCP) server for cross-platform ad management. Create, analyze, and optimize campaigns across from any MCP-compatible AI assistant.
B站（Bilibili）MCP Server —— 让 AI 助手直接操作B站。
Automate supported timeline, media, audio, effect, caption, graphics-template, and export workflows through Claude, GPT, or another Model Context Protocol client.
A Model Context Protocol (MCP) server that queries multiple Ollama models and combines their responses, providing diverse AI perspectives on a single question.
Godot MCP bridges the gap between AI assistants and the Godot game engine by providing a standardized Model Context Protocol interface.
A Model Context Protocol (MCP) Server for Joplin that enables note access through the Model Context Protocol. Perfect for integration with AI assistants like Claude.
A Model Context Protocol (MCP) for analyzing and querying GitHub repositories using the GitHub Chat API. Official Site: https://github-chat.com
Seamlessly integrate Wolfram Alpha into your chat applications.
MCP server (Model Context Protocol) providing LLM clients (Claude Desktop, Cursor, Windsurf, etc.) with tools to manage a Remnawave VPN panel.
Agent Skills
Curated, security-first OpenClaw skills (Markdown-based). Security audit skills - detect prompt injection, supply chain attacks, credential leaks. Works with Codex CLI, Claude Code, any LLM.
A skill pack that turns your coding agent into a PlanetScale database reviewer and operator. Point it at an organization and it audits configuration, query behavior, open recommendations, and safety...
817 structured cybersecurity skills for AI agents · Mapped to 6 frameworks: MITRE ATT&CK, NIST CSF 2.0, MITRE ATLAS, D3FEND, NIST AI RMF & MITRE F3 (Fight Fraud) · agentskills.
Agentic memory in a single SQLite file. Stop letting your agent re-read the same notes every session.
A repository for storing my dotfiles and AI config.
开发真正的应用很难。GSD、BMAD、Spec-Kit 等方法试图通过接管流程来帮忙。但在这么做的同时，它们剥夺了你的控制权，并且让流程中的 bug 极难排查。
Run OpenClaw, (formerly Moltbot, formerly Clawdbot) on Cloudflare Workers
A股全栈数据工具包 · 十一层架构 · 54端点 · 19数据源 · 零鉴权 | Full-stack China A-share data toolkit for AI agents — 11 layers, 54 endpoints, 19 sources, zero-auth
Unofficial Python CLI for Google Flow. Drive Veo (image-to-video, text-to-video) and Imagen (text-to-image) from your terminal: scripted, batched, pipeline-ready.
A skill library for people that make stuff
Smart memory for AI agents — Claude Code & OpenClaw
把前任蒸馏成 AI Skill，用ta的方式跟你说话。