Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Gives AI agents eyes and hands into running React Native apps: logs, REPL, tap, screenshots
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
EXECBRO_API_URL你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"execbro": {
"command": "npx",
"args": [
"-y",
"execbro"
],
"env": {
"EXECBRO_API_URL": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add execbro --env EXECBRO_API_URL=your-value -- npx -y execbro运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"execbro": {
"command": "npx",
"args": [
"-y",
"execbro"
],
"env": {
"EXECBRO_API_URL": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"execbro": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"execbro"
],
"env": {
"EXECBRO_API_URL": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
EXECBRO_API_URL env这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月6日
注册名称已通过域名 execbro.com 验证(注册中心会核实域名所有权)
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(2.19.0)于8天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Tensorust Ontology
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Who owns and controls US companies, homes and aircraft, and which federal rules apply to them.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Give your AI assistant eyes and hands into your running React Native app. Like Chrome DevTools — but for AI agents.
Build, debug, and verify features end-to-end — without leaving the chat.
ExecBro is the runtime bridge between your AI coding assistant and your running React Native app — exposing MCP tools to read logs and network, inspect component state, capture screenshots, tap the UI, and run JS. Zero config, no SDK or code changes required to start — and installing the optional SDK is recommended for the most robust log and network capture.
npm start / expo start)Log in at [execbro.com](https://execbro.com) to see your ExecBro activity rendered back to you: which tools you use most, tool error rates, and your session history — so you can spot flaky tools, track usage over time, and understand how your agent drives the app across sessions. It's built from the same anonymous telemetry described in Telemetry & Privacy, tied to your installation ID.
Linking is only for the dashboard: it attaches your installs to your account so the stats are yours. Nothing in the tooling is gated behind it.
console.log, warn, error, info, debug with filtering and search. Note: on a cold start (first app launch), logs emitted before the MCP server connects are missed — subsequent reloads capture everything. Install the optional SDK to buffer logs from the very first line of app startup_debugStack via Metro symbolication. Works on React 19, where _debugSource no longer exists. Selections are buffered in the background, so taps you make during a manual inspector session are captured without asking the agent firsttap tool with automatic fallback chain: fiber tree → accessibility → OCR → coordinates. Auto-detects platform, accepts coordinates from screenshots and layout tools unchanged. Returns post-tap screenshot and verifies visual change by defaultswipe tool that auto-routes to iOS or Android based on the connected device. Takes coordinates in the same screen space as the layout tools and screenshots — no conversion — and returns a verification.meaningful signal so agents detect end-of-list, non-scrollable surfaces, and missed coordinates — and on a screen with no React Native connection it says it could not inspect rather than guessing. Essential for scrolling virtualized lists (FlatList/SectionList) where off-screen items aren't in the fiber treepinch tool that sends two genuine kernel touch contacts through the Android emulator's multi-touch bridge, so it zooms maps, galleries, WebViews, and native views alike — it works below the app, not through React Native. Returns the same verification.meaningful signal as swipe, and refuses on unsupported targets instead of faking a resulttap with duration, resolving the target by testID/text/component), key events, and text input on both platforms. input_text targets a field itself and verifies the write by reading it back; on Bridgeless/Fabric apps replace:true overwrites pre-filled values by updating React state through onChangeText, so controlled components (Formik, react-hook-form, useState) stay consistent. native:true types into whatever the OS reports as focused, with no RN connection needed, and dismiss_keyboard operates the same way[secret:auth_api.acme.io]) whether it appears in a network header, a Redux store, a log line or a URL. Credential headers are matched by pattern rather than a fixed list, so vendor-namespaced ones (x-shopify-access-token, x-goog-api-key, x-hasura-admin-secret) are covered too, while x-request-id and x-idempotency-key are deliberately left alone. There is no per-call escape: EXECBRO_REDACT=off is set by a human and needs a restartlist_secrets names the handles; http_request({auth:{secret:"api.acme.io"}}) substitutes the value host-side and issues the request from your machine — as Authorization: Bearer by default, or in a key header or another scheme, so a credential never has to be pasted in to cover an unsupported shape, and vault_capture reads a token out of the app straight into the vault when no captured request revealed one. Each credential is bound to the origin it was observed on and refused elsewhere; the vault is memory-onlyhttp_request runs from the host with none of the app's TLS trust, proxy, cookie jar or mock rules; app_request runs inside the app with all of them. Comparing the two is how you tell a backend bug from a client one — and a 401 from the host where the app succeeds is itself the answer that the backend enforces attestationscan_metro automatically discovers and connects to all Bridgeless targets on each Metro portdevice parameter for targeting specific devices by name (case-insensitive substring match)chromium target alongside your simulators, and every tool takes the same device argumentnetwork_mock, network_condition), execute_in_app, debug globals, Redux, http_request / app_request, React component inspection (get_component_tree, find_components, inspect_component), including on Vite apps whose DevTools hook has no renderers, plus screenshot, tap, input_text, swipe (mouse-wheel scroll, and a real drag with four coordinates) and press_key (Enter, Escape, Tab, arrows, shortcuts). JavaScript dialogs (alert / confirm / prompt / beforeunload) are reported by the tool that opened them instead of timing out, page tools refuse while one is open, and handle_dialog accepts or dismisses it. Taps find elements by data-testid / id, visible text or React component name and click with real CDP mouse events. Screen reading without a screenshot: get_screen_state (tap-ready elements, what an overlay blocks), get_screen_layout, inspect_at_point and measurepinch, navigate and the other mobile-only tools refuse a chromium target with a message saying so, rather than acting on the wrong device. Native HTML5 drag and drop (draggable) and hover are not handled yetelectron_launch_app({ projectPath: "path/to/app" }) starts an Electron project from its source folder with the debugging port open and connects its windows. It runs your project's own electron or electron-vite, never a packaged buildscan_metro. Port 9222 is listed but not auto-connected, because connecting injects a network interceptor into the page. Attach with connect_metro({ port: 9222, device: " " }), or set EXECBRO_CHROMIUM_PORTS=9222 to auto-connect if (!app.isPackaged) app.commandLine.appendSwitch('remote-debugging-port', '9222')
Keep the !app.isPackaged guard: an open debugging port on a packaged build lets anything that can reach it run code in your renderer
execbro-sdk-android in its debug build registers named state and commands. scan_metro finds it over adb, list_debug_globals and inspect_global read its state, run_app_command runs its commands, navigate drives Jetpack Navigation, and screenshot captures the screenEXECBRO_CHROMIUM_PORTS)只显示了开头部分;其余内容请在仓库中阅读