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
MCP server connecting to Kubernetes
Give any AI agent eyes and hands inside any running app. 10 platforms. Zero test code. One MCP server.
Multi-instance IDA Pro MCP server — analyze multiple binaries simultaneously through a single MCP endpoint.
MCP server for AutoCAD LT automation and headless DXF generation.
An MCP server that gives AI assistants (Claude, Cursor, ChatGPT, etc.) access to SAP documentation through a unified search and fetch interface.
Stop exporting CSVs. Start asking your AI agent questions.
Um MCP Server que fornece acesso programático à API do Portal da Transparência do Governo Federal brasileiro através do protocolo MCP.
一个基于 .NET 的 Windows 桌面自动化 MCP (Model Context Protocol) 服务器，为 AI 助手提供与 Windows 桌面环境交互的能力。
MCP server paired with a browser extension that enables AI agents to control the user's browser.
Enable Claude Code, Codex, OpenClaw, and other AI agents to safely invoke Stata on your local device for data analysis.
mcp-context-protector is a security wrapper for MCP servers that addresses risks associated with running untrusted MCP servers, including line jumping, unexpected server configuration changes, and...
Harness-Engineered Browser Automation The MCP server that drives and guides AI agents through a real Chrome.
Agent Skills
面向 Codex 的长篇中文小说生产 Skill：以可恢复的 Markdown 工作流贯通灵感、规划、章节写作、审校与连续性管理。
Autonomous AI Agent Skill for Google AI Edge Gallery - self-evolving, 100% offline
GitX is a portable AI-agent skill for creating clean Git commits, tagged branches, and safe pushes across Codex, Claude Code, Cursor, and other skills-compatible agents.
Fact-checking and disinformation detection skill for Claude and Codex
Custom proactive skills for Azure SRE Agent — governance, cost intelligence, architecture quality, AI workload posture
AstrBot skill for codeagent!
Open-source legal AI agent skills for PKULaw, citations, and DOCX workflows
A benchmark and generation framework for malicious agent skills.
可执行、可复核的缠论(缠中说禅) AI Agent Skill —— 先定级别·先认结构·先写失效点。研究/学习用途,不荐股。An operational 缠论 (Chan Theory) Skill for AI agents; research only.
decision clarity
Turn your markdown vault into a compounding knowledge wiki (Karpathy inspired). Six agent skills - knowledge grows with every conversation. Works with Obsidian, Logseq, etc.
面向 Codex 的社区安全审计 Skill：用于授权 CTF、上线前安全检查、项目加固和 AI 安全报告整理