Claude Desktop インストールガイド
ローカル MCP 設定に対応するデスクトップクライアント。
MCP Servers
一个基于 MCP (Model Context Protocol) 的 Java 反编译工具，使用 CFR 反编译器对 .class 和 .jar 文件进行反编译。
一个功能强大的数据库操作 MCP (Model Context Protocol) 服务器，聚焦 （主流 + 特定场景 + 国产化/信创），支持 ，让 AI 助手能够安全、便捷地执行数据库操作。
Think MCP is an implementation of an MCP (Model Context Protocol) server that provides a "think" tool for structured reasoning in agentic AI workflows.
A Model Context Protocol (MCP) server for comprehensive threat modeling with automatic code validation.
A self-hosted web application for managing AI skills, workflows, and contexts with full MCP (Model Context Protocol) integration.
Securely inject secrets from vault systems into MCP (Model Context Protocol) servers without exposing credentials in configuration files.
Zero burden, ready-to-use Model Context Protocol (MCP) server for interacting with MySQL and automation. No Node.js or Python environment needed.
A full write-up can be found here: https://blog.securitybreak.io/building-a-threat-intelligence-genai-reporter-with-orkl-and-claude-a0ae2e969693
A Model Context Protocol (MCP) server that provides programmatic access to the Supabase Management API.
AI 驱动的 Android 动态分析工具。通过 MCP (Model Context Protocol) 让 AI 直接操控 Frida，实现自动化逆向分析。
A Model Context Protocol (MCP) server for Gradle. It gives AI agents the tools they need to explore project structures, run tasks, audit dependencies, and interact with the JVM runtime.
一个专业的、AI驱动的图表与原型绘制MCP服务器。它深度集成了智谱AI、OpenAI、Gemini等多种大语言模型，能够根据自然语言描述，智能生成**的 draw.io 格式图表和 HTML 交互式产品原型。
Agent Skills
🚀 OpenManus-Max An Advanced Autonomous AI Agent Framework with Multi-Level Permissions & Trust Attenuation
A flexible and powerful AI agent library for Python, designed to build agents with tool support, multimodal capabilities, and streaming responses.
A collection of advanced agentic tools, skills, and workflows designed for the Antigravity AI coding assistant.
面向中文用户的 。项目基于 learn-claude-code 的 Agent 工程思路改造，用 Python + Aliyun DashScope/Qwen 实现一个只读 PR Review Agent：读取 Git diff 和 PR 描述，组织多个 reviewer 生成候选问题，再通过 debate loop 对 finding...
- : write in rich text or raw Markdown, switch anytime - : fully Obsidian-compatible - : a daily capture stream for quick notes, accessible from anywhere - inspired by Raycast: find anything as you...
A tiny skill that surfaces relevant terms of art as you work with agents, growing your domain vocabulary over time
一个可开新档的 AI 健身教练框架：训练记录、RPG 属性成长、剧情推进三者联动
A Swift library for macOS automation — mouse, keyboard, screenshots, image recognition, and AI-powered agents.
macOS 可用 · Windows beta · DeepSeek API key · 非商业使用 English README
只需要一句指令，就能让 Codex 把 GPT Image 2 生成的美观图片转换为 PPTX；然后在 PowerPoint 中选择**或**，即可编辑重建后的各个元素。注意， 如果要编辑比较底层的元素可能需要多次的**，因为我们的重建逻辑涉及多层次的 元素组合。
adds rollback/recovery, adaptive context loading, and model routing intelligence on top of the original GSD by TÂCHES. Synced with upstream v1.24.0.
PhD students spend weeks on literature surveys. Most of that time is plumbing — finding papers, extracting claims, cross-referencing terminology, building comparison tables, chasing citation chains.