Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Production MCP server for multi-agent AI research. Plan, parallelize, synthesize.
Play Netflix / Apple TV+ / YouTube / Spotify by name. Cast URLs. Multi-room audio. AI concierge. All from your terminal.
- Node.js (v18 or higher) - npm (comes with Node.js) - Cursor IDE (recommended)
A defensive MCP server for Claude Desktop / any MCP client — the blue-team counterpart to offensive tooling.
It's been a constant struggle trying to understand unfamiliar and complex codebases - managing cognitive overload and trying to imagine how everything fits together.
“Hey, I’m a coding agent. I just created flashy nifty feature… but oops, I downgraded the coverage 🤓. How could I know that?”
A DBA toolkit, an MCP server, and a vim-mode SQL editor — in one static binary.
AiDex is an MCP server that gives AI coding assistants a memory, semantic search, and live telemetry — local-first, model-agnostic.
engraph — Vault Intelligence for AI Agents
Any AI coding agent (Claude Code, Cursor, Codex, Windsurf, Cline, Aider) can invoke CodeInspectus to scan AI-generated / "vibe-coded" code for real vulnerabilities, map findings to compliance...
Built by CyclSales — AI-powered CRM for real estate investors.
Search global patents and scientific literature in natural language, directly inside Claude, Cursor, or any MCP-compatible AI tool.
Agent Skills
micro-agent orchestrator for local agents
你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
Curated guidance for AI assistants building MapLibre applications — covering ecosystem and open-source best practices.
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot,...
Public repository for Agent Skills
Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, security risks, prompt injection, data exfiltration, and supply-chain risks in Claude Code, Codex, and MCP skills...
Generate draw.io diagrams from natural language — 11 presets (UML, SysML/MBSE, BPMN, network, C4…), 39 tools: codebase/CI/infra-to-diagram, image→editable diagram, Databricks product icons, mind...
The awesome collection of OpenClaw skills. 5,400+ skills filtered and categorized from the official OpenClaw Skills Registry.🦞
adds freshness decay (time-weighted memory), claim verification (verify_file_path MCP tool), 12 MCP tools (was 8), and 30+ bug fixes.
Qiushi-Skill: Build agents that investigate first, focus on the main contradiction, validate in practice, and keep pushing until the work is actually done.
首先感谢 Andrej Karpathy 的《LLM Wiki》原文。这个项目直接受那篇 idea file 启发而来。