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

DockaShell is an MCP server that gives AI agents isolated Docker containers to work in. MCP tools for shell access, file operations, and full audit trail.

The Python brain behind the Dive desktop app — also runnable standalone as a service or library.

A production-grade MCP (Model Context Protocol) server that bridges Claude Code with Perplexity's Comet browser for autonomous web browsing, research, and multi-tab workflow management.

A Model Context Protocol (MCP) server for interacting with the Solscan Pro API for Solana blockchain data.

A persistent, multi-agent server. Continuum gives AI coding agents — Claude Code, OpenCode, Codex, Gemini CLI — a shared, live view of a codebase and a memory that survives across agents and sessions.

一個簡單易用的網頁工具,用於管理 GitHub Copilot Coding Agent 的 MCP (Model Context Protocol) 設定

A Model Context Protocol (MCP) server that provides detailed type information from .NET projects for AI coding agents.

Production-ready Playwright test automation starter for teams and startups: strict TypeScript, Page Object Model, environment management, interactive runner, custom HTML reporting (with optional JIRA...

A Model Context Protocol (MCP) server for Uptime Kuma version 2. Supports stdio and streamable HTTP transports.

Model Context Protocol (MCP) server for integrating Redash with AI assistants like Claude.

Retrieval-augmented search, hooks, and an MCP server in a single local system. No API keys, no cloud dependencies.

MCP-PDB provides tools for using Python's debugger (pdb) with Claude and other LLMs through the Model Context Protocol (MCP).
Agent Skills

A Claude Code / Claude Desktop skill for creating and reading XMind mind maps. Zero npm dependencies — uses only Node.js built-ins.

一个给 Agent 使用的 Cloudflare Tunnel workflow skill。它可以把本地 HTTP/HTTPS 服务暴露到公网,支持两种模式:

A Claude Code / Cowork skill that interviews you relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.

让 Claude Code 拥有一支 12 人 AI 软件开发团队 + 1 位总指挥,从需求到上线全流程自动跑通。

✅ AI governance skill for Claude Code | AI 治理框架 | AI ガバナンスフレームワーク — Safety gates, evidence rules, anti-slack

Complete UI/UX system for Claude Code -- 152 agents, 70 plugins, 76 commands, 74 skills

JourniOne 旅行规划 Skill:从灵感与逐日路线,到带地图、可分享的 Travel Journal,按需衔接酒店与航班。

A Claude skill that walks you through writing a systematic literature review following the PRISMA 2020 framework.

- 读完 README 和 CLAUDE.md 后,可以引导用户完成配置 - 用户遇到问题时,主动提出"我可以读 docs/FAQ.md 帮你排查" - 用户有功能想法时,主动说"我可以帮你提交到 GitHub" - mycc 的 cc 会定期读取 Issues,你提交的建议会被看到

Power Platform & Azure で業務システムを開発する際に利用できるAIファースト開発標準。クイックスタートを見て利用してください。

Multi-agent adversarial code review for any coding agent

ARM64 函数级 VM 执行与指令跟踪框架。把任意 native 函数放进 Unicorn 引擎中执行,暴露每条指令、外部调用、SVC、内存访问的全部细节。 支持多进程,多线程,多并发,多个函数同时追踪,测试抖音,美团,等大型app均无崩溃情况。