Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Give agents controlled browser sessions for research, QA, screenshots, and web tasks.
Volcengine MCP Servers
Lighweight CLI to interact with MCP servers
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Draw.io Model Context Protocol (MCP) Server
A Model Context Protocol (MCP) server that enables secure interaction with MySQL databases
One home for every agent. A free, open-source app to manage all your AI coding agents — desktop, CLI, or web.
Agent-MCP is a framework for creating multi-agent systems that enables coordinated, efficient AI collaboration through the Model Context Protocol (MCP).
Telegram MCP server powered by Telethon to let MCP clients read chats, manage groups, and send/modify messages, media, contacts, and settings.
FreeCAD MCP(Model Context Protocol) server
🧠 The AI-native memory framework for building intelligent, context-aware applications 🧠 Built with Rust, Cortex Memory is a high-performance, persistent, and intelligent long-term memory system...
A lightweight, rollbackable, and visual Long-Term Memory Server for MCP Agents. Say goodbye to Vector RAG and amnesia.
Agent Skills
- 🤝 团队与**达成合作，Supervisor-Skills 正式作为**的核心科研技能完成部署，驱动「」与「」两大官方能力，将本项目沉淀的科研方法论带给亿级用户。 - 🚀 ：新增 paper-writer（证据门控的论文正文写作）、paper-polish（忠于原意的语言润色）、deep-research（综述级文献调研）三个技能；intro-drafter...
A Claude Code plugin that maintains FILETREE.md — a one-line description per file with content hashes for staleness detection.
Point it at an existing site and it finds the generic patterns, the missing states, and the sloppy code, then fixes them in place without rewriting your project.
DeepClause Typescript DML SDK and runtime
of cursor/plugins/pstack — kept in sync for standalone use. See also backnotprop/bro, referenced by the /bro skill below.
A股全栈数据工具包 · 十一层架构 · 54端点 · 19数据源 · 零鉴权 | Full-stack China A-share data toolkit for AI agents — 11 layers, 54 endpoints, 19 sources, zero-auth
Structured workflow packs for AI coding assistants, with built-in conversation memory, project memory, and learning-oriented collaboration patterns.
FTE+AI is an end-to-end program execution framework that guides R&D organizations through the complete journey of vendor replacement—from initial planning through successful cutover and optimization.
AI-native quantitative research framework
Anti-laziness skill for AI agents. Core: the Depth Tree method, which splits a task N layers deep and gives every leaf the full time budget of the whole task, so effort multiplies with depth.
Open-source Environment toolkit of claw-like agents, support task/harness generation and evaluation
Spec docs drift from code, or they bloat every PR. Skeeper picks neither.