Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
mcp server for openweather free api
The open-source security gateway for AI agents. Policy enforcement, threat detection, and compliance-ready audit logging for MCP and any AI agent framework. 🛡️
Local-first CLI + MCP server: Any file → AI-ready Markdown + JSON
A demo MCP server showcasing interactive UI capabilities using the MCP Apps Extension (SEP-1865).
VoidMob MCP server for mobile proxies, non-VoIP SMS verifications, dedicated private numbers and global eSIMs.
This MCP server helps to build structured documentation system based on Cline's Memory Bank pattern for context preservation in AI assistant environments.
X/Twitter research MCP for Claude, Cursor, Windsurf and any MCP-compatible AI agent
AppControl MCP is a local server connecting AI agents and IDEs like Claude, Cursor, and Windsurf to system history provided by the AppControl desktop app.
Turn any video — YouTube, Instagram, TikTok, Loom, X, Vimeo, direct links, local files — into transcripts, key frames, OCR text, and metadata for AI agents.
MCP server that gives AI agents full vision and control over Android devices via ADB and scrcpy.
A comprehensive and efficient MCP server for task management with multi-format support (Markdown, JSON, YAML)
An MCP server that searches your notes by meaning — reusing the embeddings the Smart Connections Obsidian plugin already generated, and running the same embedding model locally to understand your...
Agent Skills
A local minimized harness, with simplified output and logs for self-evolve
QuantManus 是一个基于大语言模型（LLM）的智能 Agent 框架，专注于**、**和**。
A skill marketplace for academic research: from project management to literature review, making figures and writing reports and grants.
本仓库最初基于 Claude Code + Exa MCP 构建，现在新增了可移植的 skills/ 目录：每个技能都使用标准 SKILL.md（仅 name + description frontmatter）和可选的 agents/openai.yaml，便于 Codex/OpenAI 界面识别，也便于 OpenClaw 按技能目录加载。
AI skill for optimizing and troubleshooting OpenClaw workspaces. 29 providers, tiered model routing, 36-check identity audit, persistent deployment profiles, and one-liner installation across 10 AI...
LuminaCode is a local general-purpose Agent. It uses a Go backend and a TypeScript TUI, with project context, tools, skills, MCP, memory, sessions, and Agent Teams.
Run a virtual iPhone on an Apple Silicon Mac.
Agents can do almost everything now. Except trade.
AI-native quantitative research framework
This repository is a generated compatibility mirror. The editable source, Issues, and contributions live in zjp1997720/zhijian-skills.
Harness-enforced AI business research skill for Claude Code and Codex Desktop
DeepClause Typescript DML SDK and runtime