Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers

mcp-vision-server is an MCP stdio server that lets MCP clients analyze images and run OCR through an existing OpenAI-compatible vision Chat Completions API.

把 米醋 的图像接口包装成 MCP server,让 Claude Code / Codex / Cursor 等 MCP 客户端直接生图、改图、批处理、多图参考。

Printed on startup. In a real terminal the box animates in brick-by-brick (set BRICKS_BANNER=anim|static|off).

这是一个支持远程连接的模型上下文协议 (MCP) 服务器,内置了飞书 OAuth 认证。

致谢:本项目的部分理念与实践,参考、借鉴自 Discord 社区 内的相关讨论与教程,并与社区成果相互参照。

- the original community MCP server for Unusual Whales by Erik Maday.

91% of Deep Research quality · 5% of the cost · Works in every MCP client

iPhone MCP server that lets AI use iPhones

The memory substrate for AI agents and developer tools. Git-versioned, file-native, MCP-first.

Frame0 is a Balsamiq-alternative wireframe tool for modern apps. allows you for creating and modifying wireframes in Frame0 by prompting.

MCP-server that provides LLMs with easy access to open data from the Swedish Government Offices and Parliament.

- The docker image is 2GB without pre-downloaded models. Its 3.76GB with pre-downloaded models!! Too big, someone please help me to reduce the size.
Agent Skills

Meta - questioning about questioning. Question yourself till you're left with only answers.

基于 deepagents 框架集成 AutoGLM 手机控制能力的开源智能助手,可在终端中运行,并支持 Android 和 iOS 设备自动化控制。

The agent has typed, audited access to the whole system — health, config, deploys, crash recovery — running on NixOS, where every change is a transaction you can undo with one command.

- — Kontext 模型,支持多参考图、可选推理质量 - — 4 种驱动模式(文本/首尾帧/参考主体/视频编辑) - — gen_content 文本任务,产物为 output_text - — Yjs 协同编辑,8 种节点类型,实时同步 - — 项目 CRUD、素材上传入库、资产库树形管理 - — 可调用 WorkRally MCP Server 全部工具

OSpec is a document-driven workflow for AI-assisted development, helping you define requirements and changes in docs first, then drive implementation, validation, and archive through AI collaboration.

My agent skills that I use every day to do real engineering - not vibe coding.

CLI for creating Claude Agent Skills with progressive disclosure validation. Built for Claude Code to use when humans ask it to create skills.

design-image-studio 是一个面向创意与设计场景的 Agent Skill。它不是简单地把一句话塞给文生图模型,而是先读取并保留完整的 Claude 设计系统提示词,再把需求整理成设计推理和结构化 brief,最后把这些设计判断压缩成更强的生图 Prompt,并直接调用 Volcengine Seedream 生成图片。

stands for . The npm package and repository slug bmad-method-test-architecture-enterprise is a package name and never an expansion of the acronym.

Monitor Claude Code, Codex CLI, OpenCode, and Devin sessions — CPU, memory, tokens, context window, costs, branches — from a single terminal pane.

It reads your transcript, figures out what each line is actually about, routes every moment to the right kind of footage, and hands back a tight set of vetted candidates (you make the final pick).

An agent skill — for Claude Code, Codex, and any SKILL.md-compatible agent — that turns any brand, product, or industry into a .