Claude Desktop 설치 가이드
로컬 MCP 설정을 지원하는 데스크톱 클라이언트.
MCP Servers
Transparent MCP proxy that reduces the token cost of large upstream tool responses for nearly every other MCP server imaginable.
An MCP server for Basecamp 3. It lets MCP-capable clients such as Codex, Cursor, and Claude Desktop read and manage Basecamp projects through OAuth-authenticated Basecamp API calls.
An MCP server that queries public SearXNG instances, parsing HTML contents into a JSON result
Your AI assistant now remembers everything. Forever. Across every conversation.
The ngrok alternative with .local domains, a scriptable CLI, and an MCP server for AI agents
Testing and evaluation platform to chat, inspect, and debug MCP servers, MCP apps, and ChatGPT apps.
ChatSpatial replaces ad-hoc LLM code generation with . Instead of generating arbitrary scripts, the LLM selects tools and parameters from a curated registry, making spatial transcriptomics workflows...
Git-native API client with encrypted secrets.
Streamable HTTP MCP server for Claude.ai custom connectors.
移动端 AI 自动化测试平台 —— MCP 工具 + AI Agent + 可视化操控台
A modular MCP server providing AI-driven vulnerability management skills, including severity classification and automated insights.
WinDbg extension + Python MCP server. Lets MCP‑compatible clients (Cursor, Claude, VS Code + Cline/Roo) drive WinDbg with clean, validated commands. Kernel‑first; user‑mode works too.
Agent Skills
🛡️ 网络安全 · 渗透测试 · 攻防对抗 · 红蓝对抗 · AI Agent Skills
This repository contains a JetBrains-filtered and JetBrains-verified snapshot of upstream GitHub agent skills collected into a flat local directory layout for easier discovery and reuse.
Hey friends. Shawn here. I've been bootstrapping and starting companies for the past 10 years (still working hard at 996 level).
A cross-platform desktop app for managing AI agent skills. Browse, install, sync, and edit skills across 16 agents from a single interface.
这是一个 ，让 AI 能够使用 IDA Pro 自动分析恶意软件，就像人类安全分析师一样：
这是一个专为 NSFC 申请书撰写设计的 Agent Skills 集合，帮助科研人员提高申请书质量，涵盖写作指导、图表制作、文献管理和政策速查等核心环节。
Agent skills for secure smart contract development with OpenZeppelin Contracts libraries.
JDArmy BREAK stands for — an open framework for enumerating and mitigating business risks. By systematically classifying, describing, and cataloguing a wide range of business risks, it provides a...
给 Claude Code、Codex、OpenClaw 等 Agent 使用的创作者公开内容研究 Skill。
Secured by SHA-pinned GitHub Actions · npm provenance · OIDC Trusted Publishing — see SECURITY.md .
SKILL 是一种模块化、自包含的扩展包，通过提供专业的领域知识、工作流程和工具来增强 AI 的能力。你可以将它们视为特定领域或任务的"入职指南"——它们将通用 AI 助手转变为具备程序化知识的专业助手。
A collection of AI agent for CPU performance analysis and optimization on x86 Linux. The skills give an agent structured, multi-step workflows for profiling with Linux perf, identifying performance...