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

- — a dedicated adversarial agent attacks the coder's output in a structured loop (createReviewLoop) until it survives review or is rejected; consensus checkpoints and per-agent resource limits keep...

这是一个基于大语言模型和MCP(Model-Controller-Plugin)和Rag架构的网络安全智能助手项目。它旨在通过自然语言交互,帮助用户执行渗透测试任务、查询安全信息、分析流量包等。

- 小爱音箱设备控制(支持40+款型号) - 涂鸦设备精准控制 - 场景联动执行

FTShare MCP 是面向 AI Agent 的金融数据 MCP 服务,让 Claude Code、Codex、WorkBuddy、OpenClaw、Hermes 等支持 MCP 的客户端,可以通过自然语言调用 FTShare 的行情、财务、宏观、基金、期货、债券、美股和港股数据。

Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j + Ollama, with your choice of Anthropic (Claude) or Ollama as the main LLM.

wp-blockmarkup-mcp is a local MCP server that extracts, validates, and indexes every Gutenberg block from WordPress core, WooCommerce, or any block-based plugin you work with.

(formerly gsd-plugin) is a Claude Code plugin that plans, executes, and verifies your work. It asks you only about the real design and architecture decisions that need your judgment, then carries out...

This project showcases how to use the MCP protocol with OpenAI, Azure OpenAI and GitHub Models. It provides a simple demo terminal application that interacts with a TODO list Agent.

ACI indexes your code with embeddings and Tree-sitter AST parsing, then lets you search it with natural language. Results come back with exact file paths and line numbers, not just fuzzy matches.

OnebotV11 Bot as MCP Server.

— Build structures through natural-language conversations with Claude.

一个功能强大的知乎收藏夹导出工具,支持将知乎收藏夹(公开和私密)批量导出为 Markdown 格式文件。支持自定义输出路径、跨平台兼容、图片下载和 Obsidian 兼容格式。支持使用大模型API一键生成文章总结。
Agent Skills

基于 [Karpathy llm-wiki]方法论,利用 AI 持续构建和维护你的个人知识库。支持从多种素材源(网页、推特、公众号、小红书、知乎、YouTube、PDF、本地文件)自动整理为结构化的 wiki,并通过 Quartz 发布为静态wiki知识库网站。 并通过 claude_agent_sdk 调用 claude agent 使用 llm-wiki ,提供api接口对外访问服务 。

Automatically updates your terminal window title to reflect the current task Claude Code is working on. Perfect for developers managing multiple Claude Code instances across different terminals.

Offense, defense, and the reverse-engineering and code-audit core both sides share. Every skill is fact-checked against primary sources.

Every agentic runtime does the same thing: read a skill, call an LLM, execute tools, loop. SubZeroClaw is that principle written directly in C — no framework, no abstractions, no architecture...

使用表示默认遵循以下协议: ⚠️ CC BY-NC 4.0 (知识共享-署名-非商业性使用 4.0 国际许可协议)

One CLI. The whole modern .claude/ surface — settings.json, agents, skills, slash commands, hooks, PRPs — wired correctly the first time.

A pre-built configuration that gives Claude Code persistent memory, security guardrails, and structured workflows. Clone, run setup.sh, and your next session picks up where the last one left off.

PRFlow is the Claude Code plugin that closes that gap — it carries one feature request all the way to a , so you do the final review and merge, not the cleanup.

Connect external AI agents, the existing Sisyphus toolset, and SiYuan's official MCP plugin ecosystem.

輸入股票代碼,自動從 Goodinfo.tw 讀取公開財報數據,生成互動式三維財務分析儀表板。

We use Kimi-K2.5 as the MLLM and Z-Image-Turbo / Qwen-Image-2512 as the Generator. We use Sglang to serve MLLM and Diffusers to serve the Generator.

A skill that provides integration with Lightpanda, a fast headless browser optimized for data extraction and web automation.