Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers
A Model Context Protocol (MCP) server that provides YouTube video summarization and transcript extraction functionality through integration with DeepSRT's API and direct YouTube caption access.
An MCP server that provides OCR capabilities using Mistral AI's OCR API. This server can process both local files and URLs, supporting images and PDFs.
CLI and MCP server for creating images, icons, and logos with Liquid Glass effects (iOS 26+). Not affiliated with Apple .
A comprehensive MCP (Model Context Protocol) server that provides integration with LightRAG API, offering across 4 categories for complete document management, querying, knowledge graph operations,...
A Model Context Protocol (MCP) server that provides tools for searching YouTube videos, retrieving transcripts, and performing semantic search over video content.
This repo contains a simple Model Context Protocol (MCP) server built with Node.js and TypeScript. It acts as a "CSS Tutor," providing personalized updates about CSS features to a connected AI client.
A Model Context Protocol (MCP) server that enables MCP clients like Claude Desktop to interact with Bluesky.
An Amazon S3 Model Context Protocol (MCP) server that provides tools for interacting with S3 buckets and objects.
基于七牛云产品构建的 Model Context Protocol (MCP) Server，支持用户在 AI 大模型客户端的上下文中通过该 MCP Server 来访问七牛云存储、智能多媒体，直播服务等。
It is a pure HTTP client to an already-running Lisply backend. Container lifecycle is owned by docker compose — see "Running it" in the Basilisk README — or run your own Lisply backend directly on a...
An MCP (Model Context Protocol) server that exposes Sonilo's licensed music and sound-effects API to MCP-compatible clients (Claude Code, Claude Desktop, Codex).
Read-only MCP (Model Context Protocol) server for Home Assistant. Gives AI assistants (Claude Desktop, LibreChat, Cline) full observability into your smart home — entity states, automations, scripts,...
Agent Skills
A skill for AI coding agents that enables full control of Obsidian vaults from the terminal using the official (v1.12+).
内容创作者每天刷几十篇公众号文章，却常常看完就忘、难以复用； 产品经理想长期跟踪竞品选题，却苦于数据分散、评论缺失； AI 用户需要高质量语料，却缺少干净、结构化、可长期管理的本地输入。
企业级多编排 Agent 项目 从文档入库、知识路由、混合检索到证据生成、工具调用和可观测治理的完整闭环
把 UI 截图、设计稿或 App 参考图交给 Codex，让它先生成完整效果图，再拆分代码界面与 image2 位图资产，最终交付可打开、可点击、可继续修改的 demo。
是一个 OpenCode Skill，帮助你将 Markdown 文稿快速转化为可导入 PowerPoint 的 SVG 文件。
: install Prax, configure an AI key, run your first task — in under 5 minutes. No programming background required.
Single-pass SSA bytecode compiler and threaded-code stack VM for a sandboxed Python subset. NaN-boxed values, inline caching, super-instruction fusion, pure-function memoization, mark-sweep GC, full...
Voice interface for Claude Code via SIP/3CX. Call your AI, and your AI can call you.
LeoAI 面向获得合法授权的红队与安全研究场景，将主机资产、Puppet 操作控制台、平台级 AI、节点级 AI 副驾和团队协作整合在同一套 Web 工作台中。v1.0.0 引入平等的 Java/PHP Puppet 双运行时，平台根据节点能力动态装配控制台与 AI 工具；平台 AI 可以将任务委派给指定 Puppet AI，节点 AI...
Hold CapsLock or Space + a key. Navigate without leaving home row, dictate by voice, let an LLM drive your computer.
最近一直在看自动化渗透相关，尝试性写了几个框架，但是最后效果都不太满意。相反，之前当玩具写的 Skill 放在 Claude Code 里面，效果却出乎意料地好。
A simple template for creating persistent AI companions that remember you