How do I install Devloop for Claude Code?
Run `claude mcp add devloop --scope user -- npx -y devloop-mcp` in your terminal.
@vincentvella
基本情報
Drives a browser - or a native Expo/React Native app on iOS/Android - and your dev server, putting both on one correlated timeline so a browser console error and the backend stack trace from the same moment line up. For Claude Code and AI agents.
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"devloop": {
"command": "npx",
"args": [
"-y",
"devloop-mcp"
]
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。
Devloop is an MCP server that drives a browser or a native Expo/React Native app (iOS/Android) alongside your dev server, placing both on one correlated timeline. It is built for Claude Code, AI agents, and human developers.
Install by running claude mcp add devloop --scope user -- npx -y devloop-mcp or by adding the JSON config with command: "npx" and args: ["-y", "devloop-mcp"] to your mcpServers block.
get_logs, get_logs_around, get_network, export_har, diagnose.Run `claude mcp add devloop --scope user -- npx -y devloop-mcp` in your terminal.
Yes, Devloop can drive an Expo or React Native app on the iOS simulator or an Android emulator, including native logs and React Native network activity.
Yes, Devloop provides per-app scoping and a shared daemon (`devloop-mcp daemon`) that lets many agents share one browser, one dev server, and one timeline over HTTP/SSE.
Yes, Devloop includes an Electron cockpit with tabbed browser panes, a filterable timeline, an element picker, a repro builder, and pop-out windows.
Free moving quotes for AI agents from Next Generation Movers, a licensed interstate mover (USDOT 3764697). US long-distance nationwide and local DC/MD/VA. Indicative ballpark price and booking options; optional $0.01 x40
🔥 MaxKB is an open-source platform for building enterprise-grade agents. 强大易用的开源企业级智能体平台。

Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.

Model Context Protocol Servers
Hindsight: Agent Memory That Learns
コメント