Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
mcp - client 项目旨在把本地的mcp-server通过flask暴露出来，用户自建内网穿透，实现coze/dify/fastgpt等平台与本地资源进行交互。
MCP server for the — 135 tools for managing Facebook & Instagram ad campaigns, audiences, creatives, insights, catalogs, and more.
An MCP server that connects Claude Code to Google's Gemini 3.1, unlocking capabilities that complement Claude's strengths.
Claude Code skills that let Claude interact with Web of Science (WoS) through Chrome DevTools MCP.
Welcome to the Twitter MCP (Multi-Channel Platform) Server! This application helps you manage your Twitter account programmatically with a variety of powerful features.
一个基于 mijiaAPI 3.x 的产品化米家 MCP 服务。它不再要求客户端先理解 did、siid/piid/aiid 这些协议细节，而是优先面向“家庭、房间、设备名、场景名”提供更自然的查询和控制能力。
An MCP server implementation that integrates with SearXNG, providing privacy-focused meta search capabilities.
An MCP server for fetching transcripts of YouTube videos.
A Claude Code skill + MCP server setup for expert-level Google Ads campaign analysis
Connect to MCP servers right from your shell. Plugin for simonw/llm.
A focused, type-safe that lets Claude Code (or any MCP-compatible client) drive a locally-running application — read chart state, change symbols and timeframes, fetch OHLCV bars, capture screenshots.
轻便的人机共读MCP
Agent Skills
good-story 是一个给科研写作用的 agent skill。它帮你把手里的结果、图表和草稿，整理成一个证据站得住、读者听得懂、审稿人也挑不散的论文故事。
Let AI agents use the same Chrome browser you use every day.
Paper Search CLI is an agent-facing Skill + CLI package built on a standalone Node.js command line tool for academic literature work.
Agent skills for GPU kernel development — writing, debugging, profiling, and optimizing CUDA and TileLang GPU kernels.
Professional post-match team reports from — a clean Python package + an agent skill, built on the Post-Match-Report-2.0 blueprint.
The definitive list of agent skills and template libraries for generating beautiful, single-file HTML presentations — for Claude Code, Codex, Cursor, OpenClaw, and Hermes.
Split "planning by chatting with an agent" from "visualizing + executing" into two independent modules:
基于 Andrej Karpathy 提出的 LLM Wiki 模式 构建的 Agent Skill，通过四阶段流水线将碎片化信息转化为结构化、可检索、持续增长的个人知识库。
On agent | Claude Code, Codex, OpenCode, Antigravity, Copilot, Cursor, Grok-Build, Pi, Hermes, OpenClaw, etc.
A complete development workflow for AI coding tools
audit-prompt-caching is a portable Codex/agent skill for finding why LLM cache reuse fails across the request path: prompt/prefix caches, provider cache telemetry, cache-aware routing, agent tool...
Turn one human UI page flow into reusable automation capabilities, then assemble new testing flows from those capabilities instead of recording everything again.