Verbindet einen AI Coding Agent mit einer laufenden React Native App, um Logs, Netzwerkverkehr, State und UI zu inspizieren sowie Fixes direkt auf dem Gerät zu testen.
Auch bekannt als igorzheludkov/execbro
- Stars
- 81
- Tools
- 11
- Downloads, 30 Tage
- 7.284
- Neueste Version
- 2.25.0
- Letzter Commit
- 15. Nov. 2026
- Lizenz
- —
Was ist ExecBro MCP?
ExecBro ist ein MCP server. Verbindet einen AI Coding Agent mit einer laufenden React Native App, um Logs, Netzwerkverkehr, State und UI zu inspizieren sowie Fixes direkt auf dem Gerät zu testen. Er stellt 11 Tools bereit, etwa scan_metro, get_network_requests, get_timeline.
Zusammenfassung generiert aus dem README des Projekts
Über ExecBro MCP server
ExecBro ermöglicht es Entwicklern, einen AI Coding Agent direkt mit einer laufenden React Native App zu verbinden. Es fungiert als Runtime-Bridge, die es einem Assistenten erlaubt, Logs, Netzwerkverkehr und den Component State zu inspizieren, bevor er versucht, Bugs zu beheben. Durch Tools zum Erstellen von Screenshots, zum Tippen auf die UI und zum Ausführen von JavaScript kann der Agent Fixes direkt auf einem Gerät oder Simulator verifizieren, anstatt sich nur auf die Code-Analyse zu verlassen.
Nutzer können sich mit iOS-Simulatoren, Android-Geräten oder sogar Electron- und Chromium-basierten Desktop-Apps verbinden. Der Server bietet spezialisierte Tools wie Network Response Mocking, um Fehlerpfade zu simulieren, sowie einen einheitlichen Tap-Mechanismus, der eine Fallback-Kette vom Fiber Tree bis hin zu OCR nutzt. Obwohl es ohne Konfiguration funktioniert, wird die Installation des optionalen SDKs empfohlen, um eine vollständige Erfassung von Logs und Netzwerk-Requests ab dem Startzeitpunkt der App zu gewährleisten. Das System enthält zudem eine Redaction-Layer, um sicherzustellen, dass sensible Credentials niemals in das AI-Transkript gelangen.
Was du damit machen kannst
- 1Runtime-Errors untersuchenBitte deinen AI Assistant, sich mit einem Simulator zu verbinden und die Ursache eines spezifischen Fehlers zu finden, der auf dem Bildschirm erscheint.
- 2Netzwerkfehler simulierenAnweise den Agenten, einen spezifischen HTTP-Response zu mocken, um zu testen, wie die App mit einem fehlgeschlagenen Request oder einer Retry-Logik umgeht.
- 3UI-Fixes verifizierenLass den Agenten einen Swipe oder Tap auf ein bestimmtes Element ausführen, um zu bestätigen, dass eine Code-Änderung ein Navigations- oder Scrolling-Problem behoben hat.
- 4Globalen Application State inspizierenNutze den Agenten, um die aktuellen Werte in Redux oder Apollo Client während einer Live-Session zu finden und auszulesen.
Geschrieben aus dem README des Projekts. Jeder Use Case wurde gegen ein Zitat daraus geprüft.
So installierst du ExecBro MCP
Formate geprüft am 10. Nov. 2026Zu Cursor hinzufügenZu Goose hinzufügenExecBro MCP in Claude Code installieren
$ claude mcp add execbro -- npx -y execbroExecBro MCP in Cursor installieren
~/.cursor/mcp.json
{
"mcpServers": {
"execbro": {
"command": "npx",
"args": [
"-y",
"execbro"
]
}
}
}ExecBro MCP in VS Code installieren
.vscode/mcp.json
{
"servers": {
"execbro": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"execbro"
]
}
}
}ExecBro MCP in VS Code CLI installieren
$ code --add-mcp '{"name":"execbro","type":"stdio","command":"npx","args":["-y","execbro"]}'ExecBro MCP in Claude Desktop installieren
claude_desktop_config.json
{
"mcpServers": {
"execbro": {
"command": "npx",
"args": [
"-y",
"execbro"
]
}
}
}ExecBro MCP in Codex installieren
$ codex mcp add execbro -- npx -y execbroExecBro MCP in Codex config.toml installieren
~/.codex/config.toml
[mcp_servers.execbro] command = "npx" args = ["-y", "execbro"]
ExecBro MCP in Gemini CLI installieren
$ gemini mcp add -s user execbro npx -- -y execbroExecBro MCP in Gemini settings.json installieren
~/.gemini/settings.json
{
"mcpServers": {
"execbro": {
"command": "npx",
"args": [
"-y",
"execbro"
]
}
}
}ExecBro MCP tools 11
Erkannt aus dem READMEscan_metroget_network_requestsget_timelineget_screen_stateget_screen_layouttappinchinput_textdismiss_keyboardexecute_in_appscreenshot
| scan_metro | — | |
| get_network_requests | — | |
| get_timeline | — | |
| get_screen_state | — | |
| get_screen_layout | — | |
| tap | — | |
| pinch | — | |
| input_text | — | |
| dismiss_keyboard | — | |
| execute_in_app | — | |
| screenshot | — |
Konfiguration
EXECBRO_API_URLOverride the license/account API base URL. Defaults to the production endpoint.
| Name | Beschreibung | Typ |
|---|---|---|
| EXECBRO_API_URL | Override the license/account API base URL. Defaults to the production endpoint. |
Automatisierte Checks
Geluften am 12. Nov. 2026Vollständiger Bericht →Unsere automatisierten Checks bestanden. Das ist kein Security-Audit: Lies den Code und gib dem Server nur den minimal notwendigen Zugriff. Wie die Checks funktionieren · Was du für mehr Punkte verbessern kannst
- Source Repository verknüpft und erreichbarBestanden
- Open Source Lizenz (OSI)No licenseBefund
- Commit oder Release im letzten JahrBestanden
- Package-Name ähnelt keinem populären PackageBestanden
- Remote Endpoint nutzt HTTPSNicht geprüft
- Destruktive Tools sind markiertNicht geprüft
- Keine versteckten Anweisungen an das ModellBestanden
- Keine kritischen Advisories im Paket oder seinen AbhängigkeitenBestanden
README
Auf GitHub ansehenExecBro
Catches what reading the code misses. ExecBro connects your AI coding agent to your running React Native app, so it can check stored data, network traffic and the real screen before it edits, and try the fix on the device before it says it's done.
On bugs where the code points to the wrong fix, Claude Sonnet 5.5 passed 14 of 18 runs with ExecBro and 9 of 18 without; Claude Opus 5.5 passed 18 of 18 with ExecBro and 16 of 18 without. Where the code alone explains the bug, both sides find it and ExecBro costs more. See the benchmark.
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 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: "<window title>" }), or setEXECBRO_CHROMIUM_PORTS=9222to auto-connectif (!app.isPackaged) app.commandLine.appendSwitch('remote-debugging-port', '9222')Keep the
!app.isPackagedguard: 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
- Efficient Buffering - Circular buffers: 500 logs, 200 network requests, 100 inspector selections
- Platform Support - Expo SDK 54+ (Bridgeless) and React Native 0.70+ (Hermes)
Setup
Add ExecBro to Claude Code in one command — no installation, npx fetches the latest version on demand:
claude mcp add execbro --scope project -- npx -y execbro@latest
Then fully restart the client (quit and relaunch) so it picks up the new server.
Project scope writes a .mcp.json you can commit, so the whole team picks ExecBro up in this repo and nowhere else. Swap project for user to register it globally instead — convenient if you work in React Native all day, but it starts ExecBro in every session you open, including repos with no Metro server to connect to.
Using a different client or need platform setup? The full setup guide covers Claude Desktop, Codex CLI, Cursor, VS Code Copilot, Windsurf, Zed, and Gemini CLI, plus Android and iOS simulator UI automation requirements.
Install the SDK (recommended)
ExecBro works with zero app changes, but installing the companion execbro-sdk package is the single biggest upgrade to debugging quality. It lets you wire up the important parts of your app — your state stores and your network layer — directly into the agent's reach, so the AI inspects real Redux/TanStack Query state and full request/response bodies instead of guessing from the outside.
| Without SDK | With SDK | |
|---|---|---|
| State stores (Redux, TanStack Query, …) | Manual via execute_in_app |
Wired up — direct references |
| Request/response bodies | Not available | Full (including GraphQL) |
| Startup network requests (auth, config) | Missed | Captured from first fetch |
| Console logs from startup | May miss early logs | Captured from first log |
| Works on Bridgeless (Expo SDK 52+) | Partial | Full |
It's one npm install plus a single init() call in your app's entry file. See the SDK guide for install, initialization, and every config option.
Requirements
- Node.js 20.9+
- React Native app running with Metro bundler
- Recommended:
execbro-sdkin your app — wires stores and the network layer into the agent for dramatically better debugging (optional; ExecBro works without it) - iOS UI automation: AXe CLI (
brew install cameroncooke/axe/axe, default) or Facebook IDB (brew install idb-companion, opt in viaIOS_DRIVER=idb) — required for tap, swipe, text input, accessibility on iOS Simulator - Optional for offline OCR fallback: Python 3.6+ (only needed when cloud OCR is unavailable, see OCR guide)
Claude Code Skills
Pre-built skills for common debugging workflows — session setup, log inspection, network debugging, and more. See the skills guide for the full list and installation instructions.
Available Tools
See the full tool reference for all tools with descriptions. Key tools:
| Tool | Description |
|---|---|
scan_metro |
Start here — scan for Metro servers and auto-connect |
get_logs / search_logs |
Capture and search console logs with filtering and summaries |
get_network_requests |
Monitor HTTP requests with method/status filtering |
get_timeline |
Actions, route changes, requests, logs and restarts in one time-ordered list |
get_screen_state |
Orientation snapshot — active route, overlays, and every element with a tap-ready (x, y) |
get_screen_layout |
Screen map of visible components with positions, sizes, and text content |
tap |
Unified tap — auto-detects platform, tries fiber → accessibility → OCR → coordinates |
pinch |
Real two-finger pinch-to-zoom — Android emulator only (iOS in progress) |
input_text |
Type text — targets and focuses a field itself, or native:true for whatever's focused. replace:true clears first (Fabric) |
dismiss_keyboard |
Blur the focused input and close the on-screen keyboard |
execute_in_app |
Run JS expressions in the app runtime (REPL-style) |
screenshot |
Take a screenshot on any platform: iOS simulator, Android, Electron or Chrome, and a USB-attached physical iPhone/iPad (capture only) |
Usage
-
Start your React Native app:
npm start # or expo start -
Just describe what you want in plain language — the agent picks the right tools. You don't need to know tool names or ask for a specific one. For example:
Connect to the simulator and investigate what caused the error on the screenCheck the network logs and investigate why this error is happeningWhy is the current screen empty? Take a look and figure it outTap the "Sign in" button and tell me what happensThe list won't scroll — scroll it down and check what's going onWhy does this button look wrong — what component renders it and where?The agent connects to Metro, reads logs and network, inspects the screen, and drives the UI as needed to answer.
Detailed Guides
| Guide | Description |
|---|---|
| Setup | Per-client MCP config (Claude, Codex, Cursor, VS Code, …), Android & iOS setup |
| SDK Setup | Install & init() the in-app SDK to wire stores + network layer into the agent |
| Console Logging | get_logs parameters, filtering, summary mode, token optimization |
| Network Tracking | SDK setup for full capture, filtering, request details, statistics |
| Network Mocking | Tutorial: force a 500, drop a field, test a retry, go offline, replay a request |
| App Inspection | Debug globals (Apollo, Redux, Expo Router), execute_in_app, limitations |
| Layout & Component Inspection | get_screen_layout, component tree, inspect_at_point, find_components |
| Device Interaction | Unified tap, platform-specific gestures, text input, key events |
| OCR Text Extraction | Cloud Vision OCR inside tap, offline fallback, language config |
| Claude Code Skills | Pre-built skills for session setup, debugging, and automation |
| Full Tool Reference | Complete list of all 62 tools with descriptions |
How It Works
- Fetches device list from Metro's
/jsonendpoint - Connects to the main JS runtime via CDP (Chrome DevTools Protocol) WebSocket
- Enables
Runtime.enableto receiveRuntime.consoleAPICalledevents - Network capture via two paths:
- With SDK: Reads from the SDK's in-app buffer via
Runtime.evaluate— captures all requests from startup with full headers and bodies, including cold-start events that CDP would miss - Without SDK: Enables CDP
Network.enable(on supported targets) or injects a JS fetch interceptor as fallback. On cold start, events emitted before the CDP connection is established are lost; subsequent reloads capture everything
- With SDK: Reads from the SDK's in-app buffer via
- Response mocking runs in that same injected interceptor: rules are matched before the request reaches the wire, and are re-pushed to every new JS context so they survive a reload
- Stores logs and network requests in circular buffers for retrieval
Connection Management
- One server per session — each agent session (each terminal or IDE window) runs its own ExecBro MCP server instance.
- Connects on request, not on startup — the server never auto-connects. It only attaches to your running React Native app when you ask it to (e.g.
scan_metro), so it stays out of the way until you actually need a device. - One driver per device — if two or more sessions in the same project point at the same Metro/device, they'll compete to control it, like a car with two steering wheels. Keep interaction to a single session per device.
- Want parallel sessions? Give each its own device + port — run separate work in a git worktree with its own Metro instance on a different port, and connect a second device (simulator/emulator) to it. For example, keep
mainon the default8081and start the worktree's Metro on8082(npx react-native start --port 8082, ornpx expo start --port 8082), then launch that worktree's app pointed at8082. Each agent session thenscan_metros and drives its own device, so the two never fight over the connection.
Troubleshooting
No devices found
- Make sure the app is running on a simulator/device
- Check that Metro bundler is running (
npm start)
Logs not appearing
- Ensure the app is actively running (not just Metro)
- Try
clear_logsthen trigger some actions in the app - Check
get_appsto verify connection status - On cold start (first launch): The CDP connection is established after the app's early initialization code has already run, so startup logs and network requests are missed. Once connected, use
reload_app— the subsequent reload captures everything from the beginning because the connection is already in place. To capture startup events on every launch, install the optional SDK
ExecBro MCP Fragen
Wie füge ich ExecBro MCP zu Claude Code hinzu?
Führe claude mcp add execbro -- npx -y execbro in deinem Terminal aus. Füge --scope user hinzu, damit der Server in jedem Projekt verfügbar ist.
Wie füge ich ExecBro MCP zu Cursor hinzu?
Öffne ~/.cursor/mcp.json und füge den Server unter mcpServers hinzu, mit der Cursor-Config aus dem Installationsabschnitt oben.
Welche Tools bietet ExecBro MCP?
Er stellt 11 Tools bereit, darunter scan_metro, get_network_requests, get_timeline, get_screen_state, get_screen_layout.
Benötigt ExecBro Änderungen an meiner React Native App?
Nein. Es funktioniert ohne Config und ohne SDK- oder Code-Änderungen. Die Installation des optionalen SDKs wird jedoch für eine robustere Erfassung von Logs und Netzwerkverkehr empfohlen.
Kann ein AI Agent Netzwerk-Requests in meiner laufenden App prüfen?
Ja, er überwacht HTTP-Requests und Responses inklusive Header, Timing und Body-Content und kann Responses mocken oder manipulieren.
Hält ExecBro Secrets aus dem Chat fern?
Ja, Tool-Outputs werden geschwärzt, sodass Credentials als Handles statt als Rohwerte behandelt werden. Der Agent kann ein Credential nutzen, ohne den eigentlichen Wert zu lesen.
Kann ExecBro iOS-Simulatoren und Android-Geräte steuern?
Ja, es unterstützt Screenshots, App-Management, Booten und Beenden auf dem iOS-Simulator sowie Screenshots, Installation und Starten auf Android.
Was muss ich tun, bevor ich meinen AI Assistant anweise, ExecBro zu nutzen?
Richte es als MCP server für deinen Agenten ein, starte deine React Native App und stelle dann einfach deine Anfrage in natürlicher Sprache.