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

Local-first knowledge compiler for humans and agents. Inspired by Karpathy's vision. Plain markdown, CLI + MCP server.

Agent Interface Compiler — One command. Every agent speaks your product. Transform OpenAPI specs into MCP Servers, Skills, CLAUDE.md, AGENTS.md, and more.

is the easiest way to connect any MCP client (like Claude or Cursor) with the browser using browser-use.

Your senior Microsoft 365, Intune, and Entra admin, installed in the AI client you already use. Agent Skills plus MCP servers for Claude Code, Cursor, Codex, Gemini, and GitHub Copilot, with a human...

Intercept AI requests, track usage, inject MCP tools centrally

You built an agent. Now you need to tune the prompt. Swap the model. Restrict access for specific users. Figure out what it's actually costing you.

Living Memory Architecture for Autonomous AI Agents — MCP server with typed connections, beliefs, decay, reconsolidation

Autonomous agents that find your clients on LinkedIn, on a server you own. An MCP server with 26 tools, so Claude or Cursor can run it. Self hosted LinkedIn outreach, AGPL, one command install.

A single-binary MCP server that connects Claude Desktop and Claude Code to Microsoft Outlook via the Microsoft Graph API.

Claude Code rewritten in Go.. High-performance AI agent harness runtime in Go. MCP server, CLI tool orchestration, session management, Kiro integration. Single binary, zero dependencies.

kali linux mcp,pentest,penetration test

Persistent, local, cross-IDE memory for AI agents — markdown source of truth, LanceDB-powered semantic search, zero cloud dependency
Agent Skills

Watchmen turns every coding session into the skill bundles you’d never sit down and write yourself.

: Claude Opus 5 (claude-opus-5) / Claude Opus 4.6 (earlier chapters) : Claude Code + OpenClaw + OpenCode : 2026-08-02 : v2026.3.9 (v2026.3.8-170-g665f67726) : https://github.

Honey (I Shrunk the AI) by GreenPT is a cross-tool coding skill that cuts AI coding-agent token usage and LLM API costs — making agents emit less code and less prose without losing correctness.

░█░█░█▀█░█▀█ ░█▀▄░█░█░█░█ ░▀░▀░▀▀▀░▀░▀ Minimal coding agent harness

Built from practice, not theory — calibrated against real deals including vLLM/Inferact ($150M @ $800M) and Hugging Face ($235M @ $4.5B).

Portable operating instructions for AI agents controlling Android and iOS devices—locally or in the cloud.

OpenAI Codex CLI 0.128 introduced /goal — a persistent agent objective with runtime audit, token budget, and a soft-stop state machine. It can drive a single task for .

Open-source repository of finance and investing skills built around the SKILL.md format.

skill infrastructure for multi-agent projects

A design skill for building never-cheap, high-craft web interfaces — both brand surfaces and product UI.

A systematic methodology for refactoring AI-generated code (Vibe Coding). Helps you discover duplicate implementations, unused resources, and inconsistent patterns.

A practical library of , , and designed specifically for QA Automation Engineers, focusing on production-oriented solutions.