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

The secure, lightweight open-source AI agent framework.

Guardrailed video editing MCP server for AI agents. Local-first FFmpeg tools, Video Receipts, quality gates, Hyperframes, and Shorts/Reels repurposing — for Claude Code, Cursor, and any MCP client.

AI-driven quality and governance MCP Server for dbt projects. Audit coverage, profile data, detect schema drift, and auto-generate documentation—all through natural language with an AI assistant.

Bring Claude Code–style sub-agents to any MCP-compatible tool.

Detect hardcoded secrets, shell injections, remote-code execution, over-privileged filesystems, and unpinned supply-chain risks across , , , and before they run.

MCP server for Flux UI component references

MCP (Model Context Protocol) server that exposes Perplexity AI search, research, and reasoning capabilities as tools.

A Model Context Protocol (MCP) server that lets AI assistants use Go’s LSP (gopls) for navigation, diagnostics, testing, coverage, and more.

A secure, hardened MCP (Model Context Protocol) server for Inkscape operations, providing both CLI actions and DOM manipulation capabilities.

Documentation | Try with Claude | Try with Goose

让 Claude、Cursor、Codex 等 AI 客户端安全地读取和操作思源笔记。

A Model Context Protocol (MCP) server that exposes Aseprite's pixel art and animation capabilities to AI assistants, enabling you to create and edit sprites using natural language.
Agent Skills

Official skills for using Brave Search API with AI coding agents.

Agent skill for production-grade ROS 2 development — from first workspace to fleet deployment.

把一堆手机拍的旅行素材,用 AI Agent 自动剪成一个完整 Vlog。 你只需要提供素材文件夹,剩下的交给 Agent。

BAGEL is a model-agnostic, modular, fully customizable Python framework for programmable protein design.

一个面向 Seedance 2.5 商业广告创作的导演型 Skill。它把产品 brief、参考图和传播目标转换为 15 秒、30 秒或自定义时长的 TVC 策略、导演执行单、分镜预览与可复制视频提示词,也能根据生成成片的时间码证据给出局部重试方案。

一个用于 的 Codex Skill。它通过 ADB 截图、UI 层级、系统运行时信息和结构化索引,把“人工逛 App”变成一套可追溯、可核验、可用于横向对比的证据材料。

本 skill 把叶子南《高级英汉翻译理论与实践》(第4版)的英译汉方法论,工程化为一条英译中流水线。核心信条如下:

Locate every paper in the literature, not just in a summary.

- using GLiNER-PII and LLM-based augmentation and validation - — LLM-generated substitute, redact, annotate, or hash (deterministic, local) - before full runs with display_record() visualization

A collection of Agent Skills that give a coding agent architectural skills to build scalable, maintainable Django projects with clean separation of concerns, testability, and a full suite of best...

OpenHarness — 24/7 Autonomous AI Framework For OpenClaw

This repository is the canonical source for a simple cloud factory: a set of agent skills and GitHub Actions workflows for moving work from an incoming issue to a verified change.