Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
一个集成 Dify AI API 的 Model Context Protocol 服务器
A Model Context Protocol server for PostgreSQL databases. Enables LLMs to query and analyze PostgreSQL databases through a controlled interface.
A Model Context Protocol (MCP) server that provides fine-grained control over a Chrome browser instance through the Chrome DevTools Protocol (CDP).
Local-first, provider-neutral Model Context Protocol server for coding-agent workflows. Routes tasks across local models (Ollama, LM Studio, llama.
This is a TypeScript-based MCP server that integrates the Kagi Search API. It demonstrates core MCP concepts by providing:
This Docker image provides a ready-to-use instance of MCPO, a lightweight, composable MCP (Model Context Protocol) server designed to proxy multiple MCP tools in one unified API server — using a...
Model Context Protocol server for the - uncensored, private AI for any MCP host (Claude Desktop, Cursor, ChatGPT, LM Studio, Continue, LibreChat, Open WebUI, AnythingLLM, Jan, Le Chat).
Put an end to code hallucinations! GitMCP is a free, open-source, remote MCP server for any GitHub project
Think DVWA but for MCP/AI agent security.
A model context protocol server for TriliumNext Notes. This server provides tools to interact with your Trilium Notes instance through MCP. You can use this MCP with triliumnext-skills.
A Model Context Protocol (MCP) server that enables AI agents (Claude Code, Cursor, and other MCP clients) to launch, interact with, and observe any Wayland application in a fully isolated virtual...
A Model Context Protocol (MCP) server that provides access to Shodan API functionality and CVE database, allowing AI assistants to query information about internet-connected devices, services, and...
Agent Skills
Self-hosted AI agent runtime — personal assistants, autonomous workers, and everything in between. Built on the Claude Agent SDK.
CEOS brings the Entrepreneurial Operating System to Claude Code, giving your leadership team 16 AI-powered skills for Vision, Accountability Chart, Rocks, Scorecard, L10 Meetings, IDS, To-Dos,...
Persistent memory for AI coding agents. Your agent remembers what it learned across sessions.
写 PRD 的人很多，能系统审 PRD 的人很少。审一份 PRD 需要同时具备业务理解、产品架构、数据建模、交互设计、商业分析等多个维度的判断力——这种能力通常需要十年以上的实战经验。
A Claude Code skill that stops you from burning through your usage limit.
Automatically audits any website across three dimensions of modern search visibility:
This repository contains a skill for zread, a CLI that generates wiki-style documentation for code repositories.
48 agents · 35 frameworks · Research-first, AI-native, depth to the Mariana Trench · Solo founder Day 0 → IPO → public company
Agents Office v3 (Beta) — a 3D isometric office where AI agents do real work on your own Claude login
Aeloon is a lightweight, high-performance, and modular AI agent framework featuring graph-driven parallel acceleration and flexible hot-swappable plugins for many usages (Deep research, Wiki,...
Opinionated, interactive health audit for a codebase. The skill scans the repo, forces a scope decision up front, then walks architecture, code quality, tests, performance, and dependencies.
Make AI understand your Xiaohongshu (RedNote)