Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
1. 下载右侧Release版本中7z文件并进行解压 2. VSCode插件库中搜索codex，安装Codex – OpenAI’s coding agent插件 3. 打开codex插件面板，点击右上角设置图标->MCP设置->打开config.toml 4. 添加如下配置
An MCP server bridging a high-capability model (Claude / GPT) to the firefox-reverse browser's built-in reverse-engineering engine.
Lets Claude (and other AI assistants) talk to your photo catalog. Search photos, set ratings, edit develop settings, manage collections, import/export — all by chatting.
An MCP server that provides tools for sending and testing in sandbox via Mailtrap.
A MCP server project that creates powerpoint presentations
As demonstrated in the video below, this plugin enables Cutter to automatically solve simple reverse engineering CTF challenges(From hack the box).
A local MCP server that connects Claude Desktop (or any MCP-compatible LLM) with your Evernote account, allowing contextual queries and searches over your notes using natural language.
Simple MCP Server to enable a human-in-the-loop workflow in tools like Cline and Cursor. This is especially useful for developing desktop applications that require complex user interactions to test.
Community-maintained MCP server for Wireshark / tshark. Not affiliated with Wireshark or Anthropic. Give your AI assistant direct access to packet captures. Ask Claude to summarize a .
This server uses the Tavily API to perform searches based on specified queries. - Search results are returned in text format.
A MCP server that send desktop notifications with sound effect when agent tasks are completed.
Your AI conversation history, queryable from any MCP-aware LLM, stored entirely on your machine.
Agent Skills
Small, composable skills for coding agents.
Formerly known as the ODIN Claude Plugin. The repo URL stays the same; the brand has matured.
English | 简体中文 | 日本語 | 한국어 | Tiếng Việt | Português | Español | Deutsch | Français | हिंदी
A curated pack of security skills for external reconnaissance, web applications, APIs, authentication, vulnerability validation, attack-path analysis, and reporting.
Режим идиоматического русского мата для AI-агентов. Короче, душевнее, эффективнее. 18+
OpenShell is the safe, private runtime for autonomous AI agents. It provides sandboxed execution environments that protect your data, credentials, and infrastructure — governed by declarative YAML...
Starter-kit for writing services in Go using Kubernetes.
LLM-compiled knowledge bases for any AI agent. Parallel multi-agent research, collector catalogs, automated session capture, feedback curation, thesis-driven investigation, source ingestion, wiki...
You don't write AGENTS.md. You train it with gradient descent.
Seu mentor de Inteligência Artificial para aprender mais e melhor na DIO.
— A self-evolving second brain powered by AI agents, markdown files, and version control. No database, no vendor lock-in — just .md files that think.
In the AI era, why can't everyone be a Principal Investigator?