ExecBro
概览
作者提供的说明(英文原文)
Catches what reading the code misses: AI agents check running React Native apps
PopNx MCP 的三大支柱
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。
- 用户评价i暂无评价评价功能将在后续阶段与账户功能一起开放
- 我们的基础检查i2 项中通过 2 项依据公开信息检查;尚未扫描代码
- 使用情况i正在增长↓ 2444/周 · ★ 81
它能帮你做什么
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。
- 连接方式: 在你的电脑上运行
- 传输方式: stdio
- 分类: 开发者工具
安装
选择你使用的 AI 应用,然后复制设置。
安装之前
- 基础检查:2 项中通过 2 项
- 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
- 需要你自己填写:
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"
}
}
}
}或者自己复制设置
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。
或者自己复制设置
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。
需要你填写的值
EXECBRO_API_URLenvOverride the license/account API base URL. Defaults to the production endpoint.
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。
哪些应用可以使用它
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
它能做什么
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。
基础检查i
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10日
- ✓ 通过
作者与仓库一致
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)
- ✓ 通过
仍在维护
代码最后更新于昨天
- … 尚未检查
有许可证
我们还没有从 GitHub 读取这个仓库
- – 不适用
端点有响应
它在你的电脑上运行,没有互联网端点
- – 不适用
使用 OAuth 登录
在你的电脑上运行,改用本地设置
- … 尚未检查
工具描述中没有隐藏指令
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“开发者工具”中的其他服务器比较i
- 星标数多于此分类中其他 5728 个服务器的 96%
- 发布到注册中心的时间比此分类中其他 5728 个服务器的 99% 更新
- 基础检查结果等于或优于此分类中其他 5728 个服务器的 100%
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。
常见问题
ExecBro 安全吗?
它在 2 项适用的基础检查中通过了 2 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。
它需要哪些密钥或代码?
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。
它在我的电脑上运行还是在云端?
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)。
它还在维护吗?
GitHub 仓库最后更新于昨天,最新版本(2.23.0)于今天进入注册中心。
哪些应用可以使用它?
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。
有什么可以替代它?
同一分类中有:REA, Netdata, Front-End Checklist
替代选择
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:↓ 每周下载量i★ 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
Netdata
Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Front-End Checklist
Review frontend code and live pages against 386 quality-gated web development rules.
作者的 README
打开 README
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。
ExecBro
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.
Get started
- Setup ExecBro as an MCP server for your agent of choice
- Setup UI automation helpers
- Install the SDK in your React Native app — optional, but recommended for the most robust log, network, and state experience
- Authorize and link to the web dashboard — optional, for usage stats and session history
- Start your React Native app (
npm start/expo start) - Ask your AI assistant in plain language — e.g. "Connect to the simulator and investigate what caused the error on the screen"
See your usage — execbro.com
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.
Features
Runtime Interaction
- Console Log Capture - Capture
console.log,warn,error,info,debugwith 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 - Network Request Tracking - Monitor HTTP requests/responses with headers, timing, and body content. Like logs, early network requests on cold start may be missed before the connection is established. Install the optional SDK for full capture from app startup including request/response bodies
- Response Mocking - Replace or tamper with HTTP responses so error paths are reached through the app's real code — the request builder, the error branch, the retry — instead of being faked by writing state directly. Simulate offline, delay responses, fail only the first attempt to test a retry, or re-issue a captured request with one field changed. Rules survive reload, and altered traffic is always tagged. See the mocking tutorial
- JavaScript Execution - Run code directly in your app (REPL-style) and inspect results
- Global State Debugging - Discover and inspect Apollo Client, Redux stores, Expo Router, and custom globals. Wire stores and other app internals straight into the agent with the optional SDK for direct, reliable state access
- Bundle Error Detection - Get Metro bundler errors and compilation issues with file locations
- Tap-to-Source - Point at any element with RN's Element Inspector and get back the absolute source file and line where it is rendered, resolved from the React fiber's
_debugStackvia Metro symbolication. Works on React 19, where_debugSourceno longer exists. Selections are buffered in the background, so taps you make during a manual inspector session are captured without asking the agent first
Device Control
- iOS Simulator - Screenshots, app management, URL handling, boot/terminate (via simctl)
- Android Devices - Screenshots, app install/launch, package management (via ADB)
- Unified Tap - Single
taptool 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 default - Unified Swipe - Single
swipetool 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 averification.meaningfulsignal 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 tree - Real Multi-Touch Pinch *(Android emulator only — iOS in progress)* - A
pinchtool 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 sameverification.meaningfulsignal asswipe, and refuses on unsupported targets instead of faking a result - UI Automation - Swipe, long press (
tapwithduration, resolving the target by testID/text/component), key events, and text input on both platforms.input_texttargets a field itself and verifies the write by reading it back; on Bridgeless/Fabric appsreplace:trueoverwrites pre-filled values by updating React state throughonChangeText, so controlled components (Formik, react-hook-form, useState) stay consistent.native:truetypes into whatever the OS reports as focused, with no RN connection needed, anddismiss_keyboardoperates the same way - Accessibility Inspection - Query UI hierarchy to find elements by text, label, or resource ID
- OCR Text Extraction - Extract visible text with tap-ready coordinates via Google Cloud Vision (works on any screen content)
Credential Safety
- Secrets never enter the transcript - Every tool's output passes one redaction chokepoint, so a token is replaced by a handle (
[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, whilex-request-idandx-idempotency-keyare deliberately left alone. There is no per-call escape:EXECBRO_REDACT=offis set by a human and needs a restart - Use a credential without reading it -
list_secretsnames the handles;http_request({auth:{secret:"api.acme.io"}})substitutes the value host-side and issues the request from your machine — asAuthorization: Bearerby default, or in a key header or another scheme, so a credential never has to be pasted in to cover an unsupported shape, andvault_capturereads 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-only - Server- vs client-side, isolated -
http_requestruns from the host with none of the app's TLS trust, proxy, cookie jar or mock rules;app_requestruns 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 attestation - App data is treated as data - The server tells every connecting agent that logs, payloads, component trees and eval results are shaped by whatever the app talked to, and are never to be followed as instructions
Multi-Device Debugging
- Connect All Devices -
scan_metroautomatically discovers and connects to all Bridgeless targets on each Metro port - Device Targeting - Every tool accepts an optional
deviceparameter for targeting specific devices by name (case-insensitive substring match) - Per-Device Buffers - Logs and network requests are captured separately per device for clean debugging
- Cross-Platform Comparison - Debug iOS and Android side-by-side, comparing logs, network traffic, and component trees
Electron & Chromium (experimental)
- Desktop React apps over CDP - An Electron window or a Chrome tab connects as a
chromiumtarget alongside your simulators, and every tool takes the samedeviceargument - What works today - Console logs, network capture, replay and mocking (
network_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, plusscreenshot,tap,input_text,swipe(mouse-wheel scroll, and a real drag with four coordinates) andpress_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, andhandle_dialogaccepts or dismisses it. Taps find elements bydata-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_pointandmeasure - Not yet -
pinch,navigateand 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 yet - Zero-config start -
electron_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 ownelectronorelectron-vite, never a packaged build - Or opt in - Add one dev-only line to the Electron main process, then run
scan_metro. Port 9222 is listed but not auto-connected, because connecting injects a network interceptor into the page. Attach withconnect_metro({ port: 9222, device: " " }), or setEXECBRO_CHROMIUM_PORTS=9222to 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
Native Android (preview)
- Kotlin apps without a JavaScript runtime - A native app that includes
execbro-sdk-androidin its debug build registers named state and commands.scan_metrofinds it over adb,list_debug_globalsandinspect_globalread its state,run_app_commandruns its commands,navigatedrives Jetpack Navigation, andscreenshotcaptures the screen - Coming soon - The SDK is not published to Maven yet. Execbro already supports it; install instructions will follow with the SDK release
Under the Hood
- Auto-Discovery - Scans Metro on ports 8081-8090 automatically, and lists Chromium/Electron targets on 9222 (plus any ports in
EXECBRO_CHROMIUM_PORTS) - Multi-Device Support - Connects to all Bridgeless targets simultaneously, with per-device log and network buffers
- Auto-Reconnection - Exponential backoff (up to 8 attempts) when connection drops
- **Effic