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
A self-modifying, self-verifying AI agent with persistent state. Reads its own source code. Plans changes. Tests them in a sandbox before applying.
MCP Server for Ozon marketplace - search products, get details, prices and delivery info
Scan your dev machine for AI agents, MCP servers, IDE extensions, suspicious files, and risky package-manager configs — in seconds.
kali linux mcp,pentest,penetration test
A mcp server that bridges Dune Analytics data to AI agents.
Add vision to text-only models in Opencode (, ) — , no manual file saving.
台灣醫療健康資料整合 MCP 伺服器 整合 ICD-10-CM/PCS、SNOMED CT、LOINC、台灣 FDA 藥品 / 健康補充品 / 食品營養，以及 FHIR R4 IG 授權與驗證工具
188+ local tools for Claude, ChatGPT, Cursor & Grok — Mail, iMessage, Teams, Slack, WhatsApp, OneDrive, Google Drive, Zoom, Outlook, Office. Native macOS, 100% local, no API keys.
MCPSafari: Native Safari MCP Server for AI Agents
The MCP ecosystem has grown to 10,000+ servers, but discovering and installing them remains painful. Existing directories — Glama, PulseMCP, mcp.so — are all closed source.
This MCP server connects your AI agent to — Google's creative suite for image and video generation. Your agent can:
The polished public release — native ComfyUI design system, live activity cards for every agent edit, and multi-tab support. Search in ComfyUI-Manager to install, or see the docs.
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