Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
A MCP server that connects to Stakpak API.
Lets Claude (and other AI assistants) talk to your photo catalog. Search photos, set ratings, edit develop settings, manage collections, import/export — all by chatting.
AI-powered MCP server for Blender with 100+ tools. Control lights, modifiers, animation, shader nodes, geometry nodes, and more from Claude, Cursor, or Windsurf.
CLI and MCP server for discovering and calling Google APIs from agents and scripts.
between your team and your AI coding agents. Define your rules once. Enforced everywhere. Every session.
An MCP server bridging a high-capability model (Claude / GPT) to the firefox-reverse browser's built-in reverse-engineering engine.
MCP server for AI image generation and editing with automatic prompt optimization and quality presets. Supports Nano Banana (Gemini), OpenAI GPT Image, and BytePlus Seedream.
MCP server for Google search and page fetching using headless Chromium
1. 下载右侧Release版本中7z文件并进行解压 2. VSCode插件库中搜索codex，安装Codex – OpenAI’s coding agent插件 3. 打开codex插件面板，点击右上角设置图标->MCP设置->打开config.toml 4. 添加如下配置
Pragmatic AI Labs MCP Agent Toolkit - An MCP Server designed to make code with agents more deterministic
MCP server for computer use & browser automation - screenshot, OCR, click, type, find_text, Chrome/Electron CDP, template matching. macOS, Windows & Android.
IFC-Bonsai-MCP is an MCP server that connects AI language models with the Bonsai Blender add-on to read, create, and edit IFC models directly via high-level tool calls.
Agent Skills
中华传统色演示、色卡浏览与颜色知识科普开源项目
Self-contained Codex and Claude Code skills for building playable, polished Three.js browser games. Install the skills, then ask your agent to use threejs-game-director; the director routes gameplay,...
A collection of skills that guide AI coding agents (Claude Code, OpenAI Codex, Google Gemini, OpenCode, OpenClaw) through common bioinformatics tasks.
Chromex is a Chrome MV3 side-panel assistant that connects Chrome to Codex through a local native bridge.
Select context for agents directly from AI-generated HTML slides
Last updated: 12.07.2026 with 26930 total repositories indexed.
An agent organization for Claude Code, structured as a company — 15+ departments, 125+ skills, each independently installable.
⚡ Power OpenClaw with Top Models — Pay 30% Less Route Claude Opus 4.6, Sonnet 4.5, and Haiku through EvoLink at ~30% off official pricing. One API key. No config changes.
My curated library of agent skills, plus the package to build your own.
这是一个用于规划小红书图文的 Agent Skill。它不是普通文案助手，而是一个“视觉导演”：先判断内容任务，再选择适合的视觉风格，最后输出完整图文结构、逐页视觉方案、图像生成提示词、发布文案和自检清单。
Read one paper deeply. Add one durable page to your academic wiki.
本skills由黄sir组学工作室的核心成员开发，三位成员为发表过《Radiology》原创性研究的第一作者（Huang Yuhong、Gu Wenchao、Song Xinyang），对影像组学领域有深刻认知。