Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
The Gemini Cloud Assist MCP server APIs are currently in Private Preview and are behind an allowlist. Please contact your Google Cloud account team to request access.
Detect Configured MCP (Model Context Protocol) in your local dev environment
MCP（Model Context Protocol）是一个让 AI 助手能够调用外部工具的协议。这个项目提供了一个必应搜索工具，让 AI 可以帮你搜索网络信息并返回结果。
The is a server built on the Model Context Protocol (MCP) that enables users to control the Unitree Go2 robot using natural language commands interpreted by a Large Language Model (LLM).
Turn your Navidrome music server into a conversational music assistant. This MCP (Model Context Protocol) server lets Claude Desktop, Claude Code, Cursor, and other MCP-compatible clients browse and...
Traditional AI chatbot interfaces are limited to text-only interactions, regardless of how powerful their underlying language models are.
This repository is a proof of concept for implementing a Model Context Protocol (MCP) client using Gradio.
An MCP server that gives AI assistants X-ray vision into HTTP traffic captured by powhttp .
A Model Context Protocol (MCP) server implementation that allows LLMs to have time awareness capabilities.
GoAtlas: The AI-Powered Code Intelligence Engine — A server-side MCP platform that deeply indexes Go/TypeScript codebases via AST parsing, builds a Neo4j knowledge graph, and provides hybrid semantic...
Todoist MCP Server A Model Context Protocol (MCP) server implementation that integrates Claude and other AI assistants with Todoist, enabling natural language task management.
A Model Context Protocol (MCP) server that extracts component information from Storybook design systems. Connects to Storybook instances and extracts HTML, styles, and component metadata.
Agent Skills
生成AIを用いて大量生産された、低品質で中身を伴わないコンテンツを指す俗語です。
Agentic browser automation and ui testing system — built with composable skills, subagent, command, and justfile layered architecture for repeatable, deployable browser use.
A skill that turns any goal into one short, paste-ready prompt. That prompt makes your agent pick a real quality bar, split the work into small pieces, run a builder and a separate harsh critic on...
AI defaults to the mean. Models are trained on millions of average websites. If you don't constrain them, they will build an average website.
주요정보통신기반시설(CII) 취약점 분석평가, AI 보안 평가, 로봇 보안 점검, 우주 보안 점검, 시큐어코딩 가이드, 제로트러스트 보안 평가, SW 공급망 보안(SBOM)을 위한 Claude Code 스킬 플러그인입니다.
这里收的东西，目标都很直接： - 能单独看懂 - 能尽快跑起来 - 能在真实工作流里省时间
· Next-Gen Transparent Agent Architecture
合乎周礼 是一个中文梗文案生成器，也是一个周礼体反向解释器。它支持两种方向： 问礼时，把普通中文改写成“大周礼时代”流行的白话翻译腔；释礼时，把周礼体翻回直接人话。 问礼会先讲一个看似古代的道理，再把现代小事放进礼法、名分、职分和体面里一本正经地论证； 释礼会拆掉这些包装，只保留原文真正想表达的意思。
One memory, not one per tool. A centralised, plain-text memory layer shared across all your AI agents and projects.
AEnvironment Everything as Environment — A Production-Grade Environment Platform for Agentic RL and Agent
31 skills for Claude Code covering the full academic research paper lifecycle — from literature search to slide generation — plus GitHub repository analysis for research topics.
gentle-pi installs in Pi: a senior-architect operating layer for Spec-Driven Development, focused subagents, strict TDD evidence, reviewable work units, safety guards, project/user skill discovery,...