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

MCP server for Klever blockchain smart contract development

- search, transcribe, compare, and cite YouTube and public social video. - import once, then search transcripts, comments, frames, and OCR without fetching the same video again.

修复了mcp连接zemax3秒超时自动崩溃的问题,zemax冷启动超过3秒导致mcp无法正常连接已修复,并且添加了实现光学系统的设计、分析与优化。本次新增四个工具:ExportAnalysisTool 支持 17 种分析类型的 BMP 图像及 TXT 数据导出,含二维数据网格的分析(PSF、波前图等)自动渲染为热力图;GeometricImageAnalysisTool 提供 25+...

LLM Reasoning Framework for Scientific Research

Zero-setup YouTube transcript extraction for Claude. Works on mobile, desktop, and web - no local installation required.

This project provides semantic search capabilities for GitHub repositories using the Model Context Protocol (MCP).

MCP Server for Phaser Editor

LLM-managed skills platform using MCP - create, edit, and execute skills programmatically in Claude, Cursor, and any MCP-compatible client without manual file uploads.

TapTap 小游戏开放能力 mcp

Search and retrieve millions of scientific papers from OpenAlex with MCP via your LLM

MCP (Model Context Protocol) server for Aspen Plus process simulation integration. This server enables AI assistants to interact with Aspen Plus simulations through a standardized interface.

Spec-driven dev workflow MCP for Cursor & AI agents — start_feature/bugfix orchestration, auto Skill+AGENTS bootstrap, memory, GitNexus. npx -y mcp-probe-kit@latest
Agent Skills

Codex Manager is a desktop configuration and asset manager for OpenAI Codex. It edits and organizes on-disk Codex files with a safety-first flow (diff preview, backups, atomic writes), surfaces local...

Gogh is a source-cited Obsidian operating brain that turns six frontend design skills into one advisable stack for AI coding agents.

A hands-off morning planning loop for Claude (Cowork or Claude Code). Every weekday it DMs you your to-dos over Slack, builds a prioritized, time-blocked schedule around your existing calendar, waits...

A collection of AI assistant skills for vLLM-Omni -- a framework for efficient omni-modality model inference supporting text, image, video, and audio.

A comprehensive Claude Skill for video and audio processing using ffmpeg. This skill provides battle-tested commands and workflows for common multimedia processing tasks.

PostHog skills (under construction)

Anything2Ontology is a 4-module pipeline that ingests raw media (PDFs, slides, spreadsheets, YouTube videos, GitHub repos, websites), extracts structured knowledge, and assembles a self-contained...

微信同事蒸馏器 — 从微信聊天记录中解密数据、查看消息、蒸馏人物 AI Skill。

🏋️ Open-source AI health coach skill — meal photo analysis, lab interpretation, body tracking, exercise programming. 600+ Chinese food nutrition database included. 开源AI健康教练。

Turn any app into a cinematic motion graphics promo video using AI.

A set of skills to steer your AI-assisted machine learning experiments. The skills help you:

On March 31, 2026, a .map file in Claude Code's npm package accidentally exposed the full TypeScript source. We read all 512,000 lines. Here's everything we found.