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

CLI-based tester for verifying that MCP servers work correctly when called directory and by agents

An AI-driven MCP server that autonomously interfaces with Malware Bazaar, delivering real-time threat intel and sample metadata for authorized cybersecurity research workflows.

A lightweight, MCPO-integrated tool that lets you (PDF, Excel, PowerPoint, Word, ZIP, etc.) directly from Open WebUI — just like ChatGPT or Claude.

OnebotV11 Bot as MCP Server.

An experimental way to connect MCPs to Pi using Code

An MCP server for reading, rendering, and searching PDF files. Built with PyMuPDF and PyMuPDF4LLM.

Complete Docker-based AI operations infrastructure: Paperclip, n8n, Supabase, OpenClaw, ruflo, and MCPs

Bilibili 视频字幕/弹幕/评论提取 MCP Server — 扫码登录,自动提取字幕/弹幕/评论与元数据,输出结构化 Markdown 供 AI 理解

用 Claude Code 直接控制你的 TradingView 桌面版。讀圖、改圖、寫 Pine Script、跑晨間掃描——全部用對話完成。

🚀 You're viewing the bleeding-edge dev docs! For other versions, check out the release/* branches.

Production-grade vector memory MCP server for Claude Code. Semantic search, per-project isolation, rules enforcement, team sharing via git.

MCP server for executing shell commands.
Agent Skills

读取本地 Claude Code / Codex CLI / Kiro / Trae / Gemini Antigravity / Cursor 的真实使用数据,自动生成**的 AI-Native 开发者画像 —— 一份长报告 + 一张竖屏海报。

专为超级个体的打造的桌面 AI 工作台,使一个人抵一个团队 code 和 work 双场景的通用智能体,Skills+ 、内置多款成熟应用、AI 应用生成与一键发布

A curated collection of specialized AI skills for WordPress development, content creation, marketing, and more. These skills follow the agentskills.

Awesome skills to use with your agents

Thin, editable harness that lets an LLM control real iOS/Android devices via MobAI. The agent writes what's missing during execution; the harness improves itself every run.

Lightweight and Memory efficient terminal for Mac built with SwiftUI and libghostty . Mac | iOS | Android | Discord

Based on your current lab repository, design your experiement panel.

为 OpenClaw 提供联网搜索能力的插件。通过飞书 / Telegram等 向 Agent 发消息,即可触发搜索、抓取网页、映射站点结构。

Χ-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?

Read it online at : fully searchable, with 108 documentation pages, 104 reference PDFs, and 212+ topics across 23 domains.

Kebab-case folders, validated YAML frontmatter, typed blocks, progressive disclosure - exported as a clean SKILL.md bundle.

Claude Code marketplace plugin — full digital chip design pipeline. 15 plugins · 16 skill files · 13 chip-design domains + infrastructure + pipeline orchestrator · closed-loop verification↔RTL...