Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
CLI and MCP server for creating images, icons, and logos with Liquid Glass effects (iOS 26+). Not affiliated with Apple .
Open-source MCP server for secure, low-latency cloud-browser automation on Kernel.
A self-contained MCP server in docker that combines the Crawl4AI, SearXNG, and Supabase to provide AI agents and coding assistants with complete web search, crawling, and RAG capabilities.
AI-powered LinkedIn analytics, content creation, and engagement automation through MCP
Bybit MCP Server enables AI assistants like , , , and other MCP-compatible clients to interact directly with the Bybit cryptocurrency exchange.
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,...
Reduce token usage. All local and open-source.
Implementation of Anthropic's MCP protocol for Firebird databases.
If your Immich library has grown past what you can manage by hand, gives any AI assistant direct access to your instance — search, organize, deduplicate, and curate albums through natural...
The most comprehensive MCP server for SideFX Houdini. 188 tools across 23 categories, covering every major Houdini context.
A Model Context Protocol (MCP) server that enables communication and coordination between multiple AI agents
A Model Context Protocol (MCP) server for accessing the OpenTofu Registry. This server allows language model assistants to search for and retrieve information about OpenTofu providers, modules,...
Agent Skills
本 skill 把叶子南《高级英汉翻译理论与实践》（第4版）的英译汉方法论，工程化为一条英译中流水线。核心信条如下：
烨笙(公众号:烨笙总Yes)开源的高质量 AI skills 合集
A Codex skill for auditing website and frontend design quality.
A Codex skill for producing consistent AI picture-book MVPs: story structure, character continuity, page prompts, layout, QA, and publishing notes.
Tapestry - 基于 Agent Skill Bundle 的轻量级书签知识库
Locate every paper in the literature, not just in a summary.
把一句视频需求、一篇实操文章、一个产品介绍，变成可执行的视频生产流程：先问清楚目标和风格，再拆脚本和分镜，再生成视觉预演 prompt，最后用 HyperFrames / Remotion / HTML / React 这类代码驱动方式生成可渲染的视频场景。
专利侵权分析系统 —— 输入专利公开号，产出竞品侵权分析报告；同时打包成 skill，可被任意 agent（dsh, codex, claudecode 等） 调用。
- using GLiNER-PII and LLM-based augmentation and validation - — LLM-generated substitute, redact, annotate, or hash (deterministic, local) - before full runs with display_record() visualization
A new version of a ballistic calculator API, a new generation light-weight, LGPL library of modelling projectile trajectory in atmosphere
A collection of Agent Skills that give a coding agent architectural skills to build scalable, maintainable Django projects with clean separation of concerns, testability, and a full suite of best...
Publora API documentation — schedule and publish social media posts across 10 platforms. For Context7 and developer reference.