Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
⭐ If Plumb saves you tokens — or designs you a page — star it on GitHub so others can find it.
A comprehensive platform that converts N8N workflows into Model Context Protocol (MCP) servers, enabling seamless integration with AI assistants like Claude, Cursor, and other MCP-compatible...
A Model Context Protocol (MCP) server implementing the "think" tool for improving Claude's complex reasoning capabilities.
A Node.js implementation of the Model Context Protocol (MCP) that provides secure shell command execution capabilities.
Learn Model Context Protocol (MCP) from scratch in plain Node.js. Build a working MCP server step by step with zero black boxes, from JSON-RPC and stdio transport to tools, prompts, resources,...
Connect AI agents to Autodesk 3ds Max through the Model Context Protocol. Ask in natural language; the agent creates objects, builds materials, inspects plugins with dedicated MCP tools instead of...
A Model Context Protocol (MCP) server implementation in Delphi, designed to integrate with Claude Code, Codex, and other MCP-compatible clients for AI-powered Delphi development workflows.
YAMCP (YAM-C-P) is a command-line tool for organizing and managing MCP servers as local workspaces. It seamlessly connects to multiple MCP servers, local or remote, grouping them into a unified...
🚀 MCP aggregator for batching multiple tool calls into a single request. Reduces overhead, saves tokens, and simplifies complex operations in AI agent workflows.
MCP server for NotebookLM - Let your AI agents (Claude Code, Codex) research documentation directly with grounded, citation-backed answers from Gemini.
AssetOpsBench - Industry 4.0: A unified benchmark and framework for building, orchestrating, and evaluating domain-specific AI agents for Industry 4.
Witsy: desktop AI assistant / universal MCP client
Agent Skills
Stop TODO leftovers, leaked secrets, sloppy commits and red CI from reaching main — with zero review bandwidth spent on the obvious stuff.
RPC messaging library for the VS Code extension platform
首先感谢 Andrej Karpathy 的《LLM Wiki》原文。这个项目直接受那篇 idea file 启发而来。
Draft Proposal (see CHANGELOG.md for version history)
它会根据角色参考图、服装参考图、场景参考图、人物关系、剧情想法和目标时长，生成更适合视频模型直接执行的完整提示词，重点处理人物一致性、情侣 POV、自然对白、微表情、手部互动、镜头连续性与真实生活感。
The system of action for AI-native cybersecurity—where intent becomes governed execution, evidence becomes operational memory, and every operation improves the next.
Developer-focused Mapbox MCP Server
AI Agent Skills for NixOS generated from docs and websites with best practices
Agent Skill and repository template for end-to-end software development entirely inside ordinary Web AI chat.
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。
Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and files it into one connected knowledge graph of plain Markdown you own.
Built for Codex, Claude Code, Gemini CLI and other coding-agent workflows. v0.1 is local-first and deterministic: it creates inspectable placeholder scene assets and an FFmpeg video without an API...