Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Shell and coding agent on mcp clients
执行 uvx mijiaAPI login -p /path/to/auth.json 登录后，在 MCP 客户端配置中添加以下内容即可接入米家：
Convert Any OpenAPI V3 API to MCP Server
"You never truly know the value of a moment until it becomes a memory."
An open-source, bilingual, AI-native Web3 curriculum for beginners, builders, and agents. 11 modules, 62 lessons, AI Tutor, badges, SEO prerendering, llms.txt, and a read-only MCP server.
An MCP server for interacting with Google Colab
AST-based call graph analysis + semantic search — right from your terminal.
just-prompt is an MCP server that provides a unified interface to top LLM providers (OpenAI, Anthropic, Google Gemini, Groq, DeepSeek, and Ollama)
The missing integration layer for AI agents. Let them call any OpenAPI / MCP / GraphQL / custom js functions in secure environment.
Generative UI examples for: AG-UI, A2UI/Open-JSON-UI, and MCP Apps.
Runno is a collection of JavaScript Packages for running code in various languages inside a sandbox. It's made of the following packages:
MCP to allow AI agents to control Unreal
Agent Skills
Comprehensive production pipeline for quad-modal AI filmmaking with Seedance 2.0
Write the feature. Do not build a bank around it. 写一个功能就写功能，不要在它外面修一座银行金库。
中文小黑怪诞正文配图生成 Skill | 16:9 白底手绘 | 少量红橙蓝批注 | Codex Skill
Read-only developer endpoint scanner for on-disk package, extension, and developer-tool metadata, built to check exposure to known software supply-chain compromises.
Penpot AI kit
Linux.do 社区用户发布的 skills 导航。这里按“能做什么、前置要求、分类标签、项目地址、Star 数、论坛来源”整理，方便快速发现值得尝试的技能。
Maintain a single YAML timeline of your career, and let AI agents generate perfectly targeted resumes for every job application — in minutes, not hours.
Claude Code port of poteto's pstack plugin (skill tree synced against upstream 4612556, pstack v0.14.2 — see What's deliberately not ported).
A comprehensive technical diagramming toolkit for , , and . Generate professional diagrams for proposals, documentation, and architecture reviews.
Claude Code / Codex skill: generate a lean, high-signal CLAUDE.md from scratch via repo scan + focused user interview.
The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.
A nightly newspaper that writes itself: an agent runs the desks, the figures come from code, and it refuses to publish an edition with marks in it.