Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
MCP (Model Context Protocol) is an open protocol that standardizes how applications share context with large language models.
Official CLI for muapi.ai — generate images, videos & audio from the terminal. MCP server, 14 AI models, npm + pip installable.
Run Model Context Protocol (MCP) servers in the browser - no local setup required!
[https://github.com/laurynas-biveinis/org-mcp/actions/workflows/elisp-test.yml] [https://github.com/laurynas-biveinis/org-mcp/actions/workflows/super-linter.yml] [https://melpa.
Model Context Protocol, or MCP, is an open protocol that standardizes how applications provide context to LLMs.
OmniMCP provides rich UI context and interaction capabilities to AI models through Model Context Protocol (MCP) and microsoft/OmniParser.
MCP server that gets Claude to 97.9% (188/192) on a real coding benchmark at -80% active tokens and -83% wall time, vs 78.3% plain. Structural code navigation + persistent memory engine.
A distributed runtime system for federated AI services with edge computing capabilities.
A CLI tool that generates Vercel AI SDK stubs for Model Context Protocol (MCP) tools. Think of it as "shadcn for MCP".
Implementation of a model context protocol (MCP) client that connects to an MCP server using HTTP streamable (recommended) transport and displays the conversation in a chat-like UI.
A CLI tool for quickly scaffolding Model Context Protocol (MCP) server applications with TypeScript support and modern development tooling
Open Source Observability Platform for MCP Servers & Apps
Agent Skills
用于 Agent Skills 的 Agnes AI 生成技能，封装 Agnes 官方文本、图片、视频 API。它采用标准 SKILL.md 结构，可安装到 Codex、Claude Code、OpenClaw、Cursor、Windsurf 等支持 Agent Skills 的客户端。
Скилл для Claude. Убирает 54 признака нейросети в русском тексте: канцелярит, кальки, фингерпринты ChatGPT и Claude. Метит в то, что меряют GPTZero, DivEye, RuBERT: поднимает perplexity и burstiness.
Three job-hunting tools bundled as an agent skill pack. Use the whole thing, or just the piece you need — each sub-folder works on its own.
HyperFrames Motion Director is an Agent Skill for turning a product story, article, README, website, or launch message into a structured HyperFrames motion-video production.
🏯 Claude Code / Codex skill — transform Chinese architecture, cultural places & travel photos into art-directed editorial posters with GPT Image. 中国古建筑与在地文化照片 → 艺术指导海报
MotionEyes is an agent-first SwiftUI motion observability system.
[comment]: <> (Table of contents generated with markdown-toc http://ecotrust-canada.github.io/markdown-toc/)
Build academic conference posters as a single HTML/CSS file, rendered to print-ready PDF via headless Chromium.
"I don't debug broken skills by hand - I have a TUI to be disappointed for me."
MapStage live tuner: map/globe, satellite, hypsometric relief, region isolate, Mapterhorn DEM, JSON presets.
/bro is a tiny Agent Skills-format skill with one job: when the assistant's last reply was too dense, too jargon-heavy, or too formal, you type /bro and it re-explains like a smart friend over a beer.
Built for (trust signals, provenance, staleness), while the rest of the ecosystem still targets v0.1.