Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
HexDocs MCP is a project that provides semantic search capabilities for Hex package documentation, designed specifically for AI applications. It consists of two main components:
An open-source MCP server that turns LLMs into condition monitoring assistants for reliability engineers. Its core design rule: .
A Model Context Protocol (MCP) server that provides AI assistants with structured access to your Logseq knowledge graph.
A Model Context Protocol (MCP) server for programmatic diagram generation using Draw.io (Diagrams.net). This server generates Draw.io XML directly — no browser extension or Draw.io instance required.
A powerful Model Context Protocol (MCP) server that provides AI-powered image and video analysis using Google Gemini and Vertex AI models.
A comprehensive Model Context Protocol (MCP) server for stock analysis and trading insights. This server provides advanced stock screening, fundamental analysis, insider trading data, social media...
This is a Model Context Protocol (MCP) server that provides integration with rust-analyzer, allowing AI assistants to analyze Rust code, get hover information, find definitions, references, and more.
An MCP server that lets AI assistants (Claude, Cursor, VS Code, …) drive your Electron app: click buttons, fill forms, take screenshots, read console logs, and run JavaScript inside it — all over the...
— This project is under active development. APIs and tool behavior may change between releases. Use at your own discretion. Feedback and bug reports welcome via GitHub Issues.
: A Model Context Protocol (MCP) server for integrating AI agents with Skywalking OAP and the surrounding ecosystem.
ProcmonMCP is a Model Context Protocol (MCP) server that allows LLMs to autonomously analyse . It exposes a comprehensive set of analysis tools to any MCP-compatible client, including Claude Code,...
A Model Context Protocol (MCP) Server for Substack enabling LLM clients to interact with Substack's API for automations like creating posts, managing drafts, and more.
Agent Skills
grill-for-unknowns combines docs/source-grounded plan interrogation with the “finding your unknowns” strategy: known knowns, known unknowns, unknown knowns, and unknown unknowns.
- ❌ ：GPTZero、Originality.ai 等工具检测出 AI 生成痕迹 - ❌ ：知网、维普等平台查重率过高 - ❌ ：语言风格不符合学术规范，逻辑不够严谨 - ❌ ：手动修改效率低，难以追踪优化进度
/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.
Turn AI output into game design decisions you can verify. Local-first · Evidence-linked · Human-gated
PersianTools provides Jalali (Shamsi) dates and datetimes that work just like Python's datetime — plus handy tools for Persian text: digit conversion between Persian, Arabic, and English, character...
Read the skill docs » · Install · Example report · 繁體中文
MotionEyes is an agent-first SwiftUI motion observability system.
把授权照片、主页截图、简介或已有角色档案，转成一套可长期复用的极简手绘图解角色；再把文章、课程、观点或脚本拆成适合传播的长文配图、知识卡、方法拆解图、手机海报或整页 PPT 演讲页面。
My agent skills that I use every day to do real engineering - not vibe coding.
Perforated is a data-efficiency layer for machine learning that adds artificial to your neural network.
Portable for writing ML/AI academic papers — from topic to compiled PDF, with verified BibTeX citations, gated workflows, and multi-agent collaboration.
Readable RTL → clear behavior → reviewable delivery Give AI the design intent, review the behavior preview, and receive artifacts you can inspect and verify.