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 Model Context Protocol server that provides access to BigQuery. This server enables LLMs to inspect database schemas and execute queries.

This is a TypeScript-based MCP server that integrates the Kagi Search API. It demonstrates core MCP concepts by providing:

Local-first, provider-neutral Model Context Protocol server for coding-agent workflows. Routes tasks across local models (Ollama, LM Studio, llama.

A Model Context Protocol (MCP) server that provides fine-grained control over a Chrome browser instance through the Chrome DevTools Protocol (CDP).

Give your AI full read/write access to Notion with . This is an agent-first : your AI client (Claude Code, Claude Desktop, Cursor, VS Code, Cline, Zed — anything that speaks MCP) can create pages,...

一个集成 Dify AI API 的 Model Context Protocol 服务器

A curated guide to convention files AI agents read, write, and act on: AGENTS.md, CLAUDE.md, SKILL.md, llms.txt, MCP configs, rules, and examples.

Educational Use Only web browsing tools. Have you used popular playwright-mcp? it is . - Here, mcp act as yourself without creating seperate browser instance.

A Model Context Protocol server for ArangoDB

https://github.com/user-attachments/assets/ab1b7e63-b6f0-4d5b-85ab-79d328de31db

⭐AI-driven public opinion & trend monitor with multi-platform aggregation, RSS, and smart alerts.🎯 告别信息过载,你的 AI 舆情监控助手与热点筛选工具!聚合多平台热点 + RSS 订阅,支持关键词精准筛选。

MCP (Model Context Protocol) is an open protocol introduced by Anthropic that standardizes how large language models communicate with external tools, resources or remote services.
Agent Skills

with Graphify + with Obsidian Zettelkasten.

现代化可灵活嵌入的任务面板,支持 Codex、DeepSeek Harness

面向 Web 逆向分析与接口签名还原场景的 Skill,围绕 camoufox-reverse MCP 构建单一工作流:先用 Camoufox 反检测浏览器完成网络捕获、源码定位、Hook 调试与反检测验证,再按需落地到 Node.js 或 Python 算法还原与自动化调用。

大多数 Markdown 笔记应用程序使用 Pandoc 将笔记转换为 Word 文档,例如我主要使用的思源笔记。然而,Pandoc 默认导出的 Word 文档样式往往不美观,不符合中文排版习惯。 幸运的是,pandoc 可以自定义 Word 模板,用于导出时的自动格式化以美化文档,但是很奇怪的是,全网很少有人分享自己是如何具体制作模板的,就算提到也只是泛泛而谈。

Professional white-box code security audit skill with 55+ vulnerability types, dual-track audit model, and multi-agent deep analysis.

本项目把传统术数相关的 AI skill 拆成可审计、可复用、可逐步扩展的工程模块。目标不是把模型包装成“更会玄学”,而是尽量减少它在排盘、流派口径、步骤顺序和解释链路上的幻觉。

AI image generation skill for Claude Code where using Google's Gemini Nano Banana models.

This repository contains sample prompts and agent instructions for Microsoft Copilot, GitHub Copilot, and Microsoft 365 Copilot.

Open Source AI trading agent that operates autonomously across 1000+ markets - Polymarket, Kalshi, Binance, Hyperliquid, Solana DEXs, 5 EVM chains.

Open Claude Tag — The open-source Claude Tag alternative

🦀 Crabwalk 🦀 Real-time companion monitor for OpenClaw agents.

Real time communication for agents. Wake on message, channels, DMs and actions. Useful for orchestrating agents.