Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
directory for Awesome MCP Servers
Knowledge graph + MCP tool server for LLM agents with hybrid retrieval, live DB sync, Korean FTS, and memory feedback.
A Stdio MCP server which proxies an SSE MCP server.
Turn any OpenAPI spec into a native CLI binary. No MCP, no bloat, no runtime dependencies, ONLY CLI.
Testing and evaluation platform to chat, inspect, and debug MCP servers, MCP apps, and ChatGPT apps.
Enhanced note taking for AI Agents with supervision.
🔥 MCP Mastery: Build AI Apps with Claude, LangChain and Ollama
One command. TypeScript Python. Example tools, the Inspector, and tests — all wired up. Or point it at an OpenAPI spec and get
This MCP server provides tools for listing and retrieving content from different knowledge bases.
The purpose of the repo is to teach you how to make MCP servers. The target audience are non-technical with no real coding experience.
The enterprise-grade TypeScript framework for building production-ready MCP servers. Decorators. Dependency Injection. Widgets. One framework to ship AI-native backends.
Generic markdown vault MCP with hybrid search
Agent Skills
A skill that helps you get a peer review on your manuscripts in preparation. Upload a manuscript (or paste an abstract), and it runs targeted Consensus searches to check whether the background claims...
Codex Dream Skin 开源换肤 Skill：支持 macOS/Windows Codex App 主题安装、自定义 Banner、主题切换、实时验证与一键恢复。Open-source Codex desktop theme tool.
Copilot ralph is an autonomous AI agent loop that runs repeatedly until all PRD items are complete.
Award-winning 3D scroll websites from ONE prompt — Claude Code + Higgsfield MCP. Generates cinematic hero shots & 3D clips (360° spins, fly-throughs, explosions), slices them into scroll-scrubbed...
不是总结论文，是重构认知。一个基于对话的 Claude sensemaking skill，帮你找到论文和你现有认知的真实摩擦点。A Claude skill for paper sensemaking: find the friction between what you read and what you actually believe, then reconstruct your...
Claude Code 学术研究技能合集 — 深度调研 · 论文写作 · 同行评审 · 人物思维蒸馏
Environment-Runtime 是一个面向工程场景的轻量级 Agent Runtime。随着 OpenClaw 在企业工程流程中的关注度持续提升，一个现实需求也逐渐显现：面向通用场景的 agent runtime 设计未必能直接覆盖所有工程落地形态。这个项目把视角收窄到高确定性工程流程，希望把常见工程任务组织成更清晰、更可复用、更容易维护的运行时。
A hypothesis-driven debugging skill for Claude Code, Codex, and Gemini CLI. Instead of blindly guessing fixes, it instruments your code with runtime logs, generates multiple hypotheses, and...
For engineers who want agents shipping code without a human in the loop.
A dual-path memory system for proactive agents. Facts and procedures in a local knowledge graph, exposed as a CLI, MCP tools and skills. No API key.
微信读书前几天上了一个官方 AI skill（weread.qq.com/r/weread-skills），把书架、笔记、阅读统计、推荐 6 件事开放给 AI。能力很强，但它只是「自然语言包装的搜索接口」——你让它推荐书，它不会去看你已经读过什么，常把你笔记 68 条的书又当新书推回来给你。
逻辑帧团队开源的自动化视频制作工具