Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers

This is a typescript based companion Model Context Protocol(MCP) server for the Drupal MCP module that works with the STDIO transport. In order to use SSE transport this server is not required.

MCP/API/WebUI to find torrents programmatically

This is a Model Context Protocol (MCP) server that provides tools for interacting with Proxmox VE infrastructure.

A Model Context Protocol (MCP) server that provides tools for reading and extracting text from PDF files, supporting both local files and URLs.

A simple Model Context Protocol (MCP) server that provides real-time weather data to AI agents like GitHub Copilot.

一個簡單易用的網頁工具,用於管理 GitHub Copilot Coding Agent 的 MCP (Model Context Protocol) 設定

:star: To stay updated and get notified about changes, star this repo on GitHub!

Purpose: Learn to build Powerful Model Context Protocol (MCP) servers by scaling tools into reusable agentic workflows (ADWs aka Prompts w/tools).

MCP (Model Context Protocol) server for Upwork via browser automation. Enables Claude Code to search jobs, manage proposals, messages, and contracts on Upwork.

Enhanced MCP code execution. Agent framework-agnostic (optimized for Claude Code). Skills framework (99.6% token reduction), multi-transport, sandboxing

A Model Context Protocol (MCP) server for AI-driven MIDI composition. Generate MIDI files from structured JSON data, with chord name support, an interactive piano-roll preview UI, and multiple...

An MCP interface/extension for Jupyter Server
Agent Skills

This is a professional Skill toolkit for writing Chinese Party and government official documents (公文).

humble A humble, and fast, security-oriented HTTP headers analyzer

A Claude Code skill that enables AI-assisted generation of macOS/iOS Shortcuts. Create valid .shortcut plist files that can be signed and imported into Apple's Shortcuts app.

— 使用、修改或部署本專案,必須標明原作者 、附上本 repo 連結,並以相同授權公開原始碼。網路服務部署亦同。 本專案於 2026/04/13 從 MIT 切換至 AGPL-3.0。此日期之前取得的版本仍適用 MIT 授權。

Catch AI mistakes before they cost weeks of compute. Reproduce papers from arxiv. Debug runs evidence-first. Compare experiments at the right epoch. Launch with discipline.

你只说一句“我要什么视频”,它把素材、分镜、字幕、转场、动效、渲染和质检组织成一个可复现的视频工程。 Say what video you want; qiaomu-cut turns it into a source-aware, renderer-ready, verifiable video project.

A skill for AI coding agents that enables full control of Obsidian vaults from the terminal using the official (v1.12+).

微信公众号文章自动创作与发布工具:从选题搜索、撰写、AI 配图、排版到发布草稿箱,一条命令搞定。可作为 Claude Code / Codex / Cursor 的 Skill,也可独立命令行调用。

使用 LangChain 1.0 构建的 Skills Agent,演示 Skills 三层加载机制的底层原理。默认使用 Anthropic,也支持 OpenAI / OpenAI-compatible 接口。

面向电商商品图生产场景的图片套图 Skill。仓库提供一套从商品图分析、卖点提炼、Prompt 组织到成图输出的脚本与配置,适合用在淘宝、京东、拼多多、抖音等国内平台,以及独立站、Amazon 等跨境场景。

— kinetic typography, data-driven charts, explainers, TikTok / Reels, 3D & WebGL, math animation, generative illustration, and web motion. Fifteen installable packs.

Turn simple scene ideas into restrained, physically believable cinematic AIGC prompts.