Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
A Model Context Protocol (MCP) server that provides tools for interacting with a Supabase database. This server enables AI assistants to perform database operations through a standardized interface.
Fetch and read Jewish texts through the API of Sefaria.org
A powerful Model Context Protocol (MCP) server that provides an access to serverless browser for AI agents and apps
An MCP server that enables interacting with the arXiv API using natural language
This project provides a Model Context Protocol (MCP) server that exposes tools for interacting with an Obsidian vault.
MCPHub Desktop 是一款基于 Tauri 2 构建的桌面客户端，用于在个人电脑上统一管理 MCP服务器、Skills、RAG 知识库。所有进程、配置、密钥与向量数据都运行/保存在用户自己的机器上，不依赖任何远端服务。
AI-powered photogrammetry automation — MCP server for Agisoft Metashape Professional 2.3+. Control the full pipeline (alignment, dense cloud, mesh, texture, DEM, orthomosaic, export) using natural...
Convert GitHub repositories to MCP servers automatically. Extract tools from OpenAPI, GraphQL & REST APIs for Claude Desktop, Cursor, Windsurf, Cline & VS Code.
: This is a community-maintained project and is not officially affiliated with, endorsed by, or supported by Datadog, Inc.
MCP server for cleaning malware from WordPress sites via SSH and WP-CLI. Batch operations for 20+ sites.
MCP server that enables AI assistants to interact with Qwen code
The most feature-complete MCP server for Obsidian vaults — 23 tools + 3 resources for search, read, write, tags, link analysis, graph traversal, and canvas. Also ships as an Obsidian plugin (github.
Agent Skills
Helixent is a small library for building ReAct-style AI agent loops based on the Bun stack.
是一个 Claude Code 插件，基于 WooYun（2010-2016）收录的 22,132 个业务逻辑漏洞案例，为 Claude 的安全测试输出注入**、**和**。
AI agent skills for image/video generation and complete visual brand systems via Higgsfield AI, including Marketing Studio and Virality Predictor video scoring.
- 只要做图片版 PPT → - 只把图片转可编辑 → - 一键"先出图再转可编辑" / 未指定 → （A→B 串联）
Claude Code skill: four-phase plan hardening (recon, interrogate, Codex adversarial review, cross-model build & inspection) — two AI models harden your plan before a line of code exists, then swap...
Lightweight Result type for TypeScript with generator-based composition.
Built for researchers, it runs on your own computer (macOS, Windows, Linux). Create a project, describe a task in plain language, and let the AI agent read files, run Python and R code, search the...
Everything for pentest. | 渗透测试知识库，以 AI Agent 可执行的格式沉淀安全方法论。
ClawTeam fork fully adapted for OpenClaw — multi-agent swarm coordination with OpenClaw as the default agent
The core of Membrane Framework, multimedia processing framework written in Elixir
A production-oriented starter kit for building AI-powered web apps with an agentic development workflow. It gives you a working Next.
微信公众号 AI 运营助手 | 选题、写稿、审稿、排版、配图、发布全流程 Skill，支持 OpenClaw / Claude Code / Cursor / Codex