Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
MCP server for Apache Iceberg
182 adversarial-input security tests, defusedxml everywhere, sandboxed writes, no patched binaries, no private APIs — plus a private disclosure channel with externally reported fixes already credited...
This repository contains the code and examples for the FreeCodeCamp course on Model Context Protocol (MCP).
MCP server for Unreal Engine 5.6/5.8 :D token-efficient Blueprint reading, editing, and a persistent project index for AI coding agents
An MCP server for automating the PlayCanvas Editor with an LLM. The MCP client is built into the Editor — no browser extension needed.
Unofficial Relace MCP client with AI features. Personal project; not affiliated with or endorsed by Relace
Bidirectional, stateful control of Logic Pro from AI assistants. Combines (CoreMIDI, Accessibility, CGEvent, AppleScript, OSC) into a single MCP server with smart routing, fallback chains, and...
MCP server for AgentHansa — auto-generated tools from the live API
Semantic F# for AI coding agents (Claude Code · Cursor · Copilot · Codex) — an MCP server that gives LLMs real FCS/FSAC compiler intelligence (find, check, types, rename) instead of grepping F#.
Grounded AI development for Dynamics 365 Finance & Operations — works with GitHub Copilot and Claude Code
A MCP server to connect to wolfram alpha API.
A powerful Model-Context-Protocol (MCP) server for interacting with Plex Media Server. It provides a standardized JSON-based interface for automation, AI agents (like Claude), and custom integrations.
Agent Skills
锻造你的知识体系 — 通用知识笔记模板 考研 · 考公 · 专业课 · 科研 · 项目 · 竞赛 · 期末
A comprehensive security review framework for AI agents operating in adversarial environments.
I'm building aven, a local-first task manager for power users and agents.
Works with the agent you already use: Claude Code, Codex, Cursor.
这是一个长期维护的 AI 视频制作 skill 精选仓库，用来沉淀我在视频创作、视频复刻、动效生成、片头包装、质检交付等流程中反复使用的方法，也用来把优秀参考视频中的动效拆成 HyperFrames / Remotion 能够实现和复用的组件。
给 Agent 一个链接，它会先选对读取通道，再把完整原文交给后续的总结、写作、翻译或分析任务。
4 risk tiers · 11 damage control procedures · 11 mission templates · 7 crew roles · 16 standing orders
A Claude Code skill that turns any API into a working CLI, then wraps that CLI in a skill. Point it at API docs, a live URL, or a peek-api capture and get a dual-mode Commander.
Essays and writing behind this toolkit live at vexjoy.com.
Office Agents is a monorepo of Microsoft Office Add-ins with integrated AI chat panels. Each add-in connects to major LLM providers using your own credentials (BYOK) and can read/write documents...
Claude Code skills that let Claude interact with Google Scholar through Chrome DevTools MCP.
🧠 A collection of reusable for Claude AI and developer tooling. Each skill is a focused, modular package that brings automation to your dev workflows — from SEO analysis to document parsing, CI/CD...