Skip to main content
Glama

ExecBro

MCP Registry

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

  1. Setup ExecBro as an MCP server for your agent of choice

  2. Setup UI automation helpers

  3. Install the SDK in your React Native app — optional, but recommended for the most robust log, network, and state experience

  4. Authorize and link to the web dashboard — optional, for usage stats and session history

  5. Start your React Native app (npm start / expo start)

  6. Ask your AI assistant in plain language — e.g. "Connect to the simulator and investigate what caused the error on the screen"

Related MCP server: React Native DevTools MCP

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, 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

  • 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 _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 first

Device Control

  • iOS Simulator - Screenshots, app management, URL handling, boot/terminate (via simctl)

  • Android Devices - Screenshots, app install/launch, package management (via ADB)

  • Physical iPhone/iPad over USB - Screenshots on iOS 15+; launching and terminating the app on iOS 17+; on iOS 27+ taps (by coordinates or testID/text/component), long press, swipe, text entry and keys, with the layout tools reading the app in screenshot pixels, via pymobiledevice3. See physical iOS setup and what was tested

  • Unified Tap - Single tap 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 default

  • Unified Swipe - Single swipe 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 tree

  • Real Multi-Touch Pinch (Android emulator only — iOS in progress) - A pinch 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 result

  • UI Automation - Swipe, long press (tap 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

  • 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, 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 restart

  • Use a credential without reading it - list_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-only

  • Server- vs client-side, isolated - http_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 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_metro automatically discovers and connects to all Bridgeless targets on each Metro port

  • Device Targeting - Every tool accepts an optional device parameter 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 chromium target alongside your simulators, and every tool takes the same device argument

  • 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, 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 measure

  • Not yet - pinch, 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 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 own electron or electron-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 with connect_metro({ port: 9222, device: "<window title>" }), 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

Native Android (preview)

  • Kotlin apps without a JavaScript runtime - A native app that includes 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 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.

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-sdk in 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 via IOS_DRIVER=idb) — required for tap, swipe, text input, accessibility on iOS Simulator

  • Physical iPhone/iPad: pymobiledevice3 (pipx install pymobiledevice3) and a mounted developer disk image; taps also need iOS 27+, pymobiledevice3 11.32.0+, Developer Mode and the Xcode 27 disk image. See physical iOS setup

  • 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. Also taps a USB iPhone on iOS 27+, by coordinates or testID/text/component

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

Usage

  1. Start your React Native app:

    npm start
    # or
    expo start
  2. 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 screen
    Check the network logs and investigate why this error is happening
    Why is the current screen empty? Take a look and figure it out
    Tap the "Sign in" button and tell me what happens
    The list won't scroll — scroll it down and check what's going on
    Why 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

  1. Fetches device list from Metro's /json endpoint

  2. Connects to the main JS runtime via CDP (Chrome DevTools Protocol) WebSocket

  3. Enables Runtime.enable to receive Runtime.consoleAPICalled events

  4. 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

  5. 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

  6. 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 main on the default 8081 and start the worktree's Metro on 8082 (npx react-native start --port 8082, or npx expo start --port 8082), then launch that worktree's app pointed at 8082. Each agent session then scan_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_logs then trigger some actions in the app

  • Check get_apps to 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

Telemetry & Privacy

No source code, file paths, or app content is ever sent. Your app and your repo stay on your machine.

ExecBro sends two small signals:

  • Product analytics (optional) — tool names, success/failure, and durations. This is what powers your usage dashboard and tells me which tools are flaky and worth fixing. Turn it off any time with EXECBRO_TELEMETRY=false in your MCP server config.

  • Usage count — a running tally of how many tool calls you've made. It's a number, not content, and it's the one signal that keeps running when analytics is off.

See the Telemetry & Data Collection guide for the full field-by-field breakdown, and PRIVACY.md for the complete privacy policy.

Supported React Native Versions

Version

Architecture

Engine

Status

Expo SDK 54+

Bridgeless (New Arch)

Hermes

✓ Fully supported

RN 0.76+

Bridgeless (New Arch)

Hermes

✓ Fully supported

RN 0.73 - 0.75

Bridge (Old Arch)

Hermes

✓ Fully supported (best network capture via CDP)

RN 0.70 - 0.72

Bridge (Old Arch)

Hermes / JSC

✓ Supported

RN < 0.70

Bridge

JSC

Not tested

Physical iPhone/iPad: what works and what was tested

Physical device support is new and has been checked on very few devices. This table says exactly what was run on real hardware and what was not.

Capability

iOS

Status

screenshot

15 - 16

✓ Tested (iPhone 6s Plus, iOS 15.8.8)

screenshot

17 - 26

Expected to work, not tested

screenshot

27+

✓ Tested (iPhone 11, iOS 27.2.1)

tap by x/y, portrait

27+

✓ Tested (iPhone 11, iOS 27.2.1; 200 taps in a row, all landed)

tap with duration (long press)

27+

✓ Tested (opened a context menu)

tap by x/y, landscape (both directions)

27+

✓ Tested

tap refuses when the screen is off

27+

✓ Tested

Tap outcome (route, text changes, network) for an RN app on the phone

27+

✓ Tested (RN 0.85 test app, iPhone 11, iOS 27.2.1)

tap of any kind

26 and below

✗ Not possible: the phone itself refuses remote touch below iOS 27

tap by testID / text / component

27+

✓ Tested (iPhone 11, iOS 27.2.1)

swipe (direction, distance, scroll offset, no-op reason)

27+

✓ Tested (iPhone 11, iOS 27.2.1)

input_text (controlled, uncontrolled, append, replace, masked, maxLength)

27+

✓ Tested (iPhone 11, iOS 27.2.1); since 2.26.2 the first word after an app launch no longer loses a character

press_key (named keys, characters, Shift on a character)

27+

✓ Tested (iPhone 11, iOS 27.2.1); modifier combos are refused

get_screen_state, get_screen_layout, inspect_at_point in screenshot pixels

any

✓ Tested (iPhone 11, iOS 27.2.1)

ios_launch_app / ios_terminate_app

17+

✓ Tested on 27 (iPhone 11, iOS 27.2.1); 17 - 26 expected to work, not tested

Reattach after the app drops off Metro

any

✓ Tested by killing and relaunching the app; a real screen lock not yet

Not tested at all yet: iPads, any iPhone other than the two above, a Mac with Xcode 27 installed (testing used Xcode 26, quit, with the Xcode 27 disk image downloaded by pymobiledevice3 mounter auto-mount), and a phone connected over Wi-Fi instead of USB. Test setup: macOS 26, pymobiledevice3 11.32.0 and 11.33. If it works or fails on your device, please tell us with send_feedback or a GitHub issue. Setup steps: physical iOS setup.

Pricing

ExecBro is free. Every tool, no cap, no account required. Linking an account is optional and only gets you the usage dashboard.

Feedback & Feature Requests

Please run this at the end of your session to help me make the tools better. ExecBro is built for AI agents, so the most valuable feedback comes from the agent itself — paste this prompt to your agent:

Write a report about your experience with the ExecBro tools — where you were struggling and what could be improved. Save it as a Markdown file for me, then submit it using the send_feedback tool (type "feedback") so it becomes a GitHub issue.

It takes 30 seconds: your agent runs send_feedback, hands you a pre-filled GitHub issue URL (environment info already attached), and you click submit — no GitHub setup, no copy-pasting. Real friction logs from real sessions are what shape the roadmap and get fixed first, so please send one. 🙏 And if you just have a quick idea or question, drop into GitHub Discussions to share feedback, request features, and vote on what gets built next.

Package names & staying up to date

Ships as the npm package execbro. The package was previously published as react-native-ai-devtools and before that as react-native-ai-debugger — both legacy names keep receiving identical builds via mirror-publish, so existing installations and MCP configs keep working unchanged. New installs should use execbro.

IMPORTANT

Already using ExecBro? npx caches packages indefinitely, so you may be stuck on an old version without realizing it. Update your MCP config to use npx -y execbro@latest (see Setup) so every session pulls the latest release with new tools and bug fixes. New installs after this change auto-update automatically.

License

MIT

Available Tools

64 tools
android_describe_allA

Get the full UI accessibility tree from the Android device using uiautomator. Returns a hierarchical view of all UI elements with their text, content-description, resource-id, bounds, and tap coordinates.

Inputs: deviceId.

android_describe_pointA

Get UI element info at specific coordinates on an Android device. Returns the element's text, content-description, resource-id, bounds, and state flags.

Inputs: x (required), y (required), deviceId.

android_find_elementA

Find a UI element on Android screen by text, content description, or resource ID. Returns element details including tap coordinates. Use this to check if an element exists without tapping it. Workflow: 1) wait_for_element, 2) find_element, 3) tap with returned coordinates. Prefer this over screenshots for button taps.

Inputs: text, textContains, contentDesc, contentDescContains, +3 more.

android_get_screen_sizeA

Get the screen size (resolution) of an Android device/emulator

Inputs: deviceId.

android_input_textA

Type text on an Android device/emulator. The text will be input at the current focus point (tap an input field first).

Inputs: text (required), deviceId.

android_install_appC

Install an APK on an Android device/emulator

Inputs: apkPath (required), deviceId, replace, grantPermissions.

android_key_eventB

Send a key event to an Android device/emulator. Common keys: HOME, BACK, CALL, END_CALL, VOLUME_UP, VOLUME_DOWN, POWER, CAMERA, CLEAR, TAB, ENTER, DEL, MENU, SEARCH, MEDIA_PLAY_PAUSE, MEDIA_STOP, MEDIA_NEXT, MEDIA_PREVIOUS, MOVE_HOME, MOVE_END, APP_SWITCH, ESCAPE

Inputs: key (required), deviceId.

android_launch_appB

Launch an app on an Android device/emulator by package name

Inputs: packageName (required), activityName, deviceId.

android_list_packagesC

List installed packages on an Android device/emulator

Inputs: deviceId, filter.

android_long_pressC

Long press at specific coordinates on an Android device/emulator screen

Inputs: x (required), y (required), durationMs, deviceId.

android_screenshotB

Take a screenshot from an Android device/emulator. Returns the image data that can be displayed.

Inputs: outputPath, deviceId.

android_swipeC

Swipe from one point to another on an Android device/emulator screen

Inputs: startX (required), startY (required), endX (required), endY (required), +2 more.

android_tapA

Tap at specific coordinates on an Android device/emulator screen. WORKFLOW: Use ocr_screenshot first to get tap coordinates, then use this tool with the returned tapX/tapY values.

Inputs: x (required), y (required), deviceId.

android_tap_elementA

Tap an element by its text, content-description, or resource-id using uiautomator. TIP: Consider using ocr_screenshot first - it returns ready-to-use tap coordinates for all visible text and works more reliably across different apps.

Inputs: text, textContains, contentDesc, contentDescContains, +3 more.

android_wait_for_elementA

Wait for a UI element to appear on Android screen. Polls the accessibility tree until the element is found or timeout is reached. Use this FIRST after navigation to ensure screen is ready, then use find_element + tap.

Inputs: text, textContains, contentDesc, contentDescContains, +5 more.

clear_bundle_errorsB

Clear the bundle error buffer

Inputs: no named parameters.

clear_logsB

Clear the log buffer

Inputs: no named parameters.

clear_networkB

Clear the network request buffer

Inputs: no named parameters.

connect_metroA

Connect to a Metro server on a specific port. Use this when you know the exact port, otherwise use scan_metro which auto-detects. Establishes the WebSocket connection needed for debugging tools.

Inputs: port.

ensure_connectionA

Verify or establish a healthy connection to a React Native app. Use before running commands if connection may be stale, or after navigation/reload. This tool runs a health check and will auto-reconnect if needed.

Inputs: port, healthCheck, forceRefresh.

execute_in_appA

Execute JavaScript code in the connected React Native app and return the result. Use this for REPL-style interactions, inspecting app state, or running diagnostic code. Hermes compatible: 'global' is automatically polyfilled to 'globalThis', so both global.REDUX_STORE and globalThis.REDUX_STORE work.

Inputs: expression (required), awaitPromise, maxResultLength, verbose.

find_componentsA

Find components matching a name pattern. TARGETED SEARCH: Use after get_component_tree(structureOnly=true) to find specific components by pattern and get their layout info. More efficient than get_screen_layout for targeted queries. Use includeLayout=true to get padding/margin/flex styles.

Inputs: pattern (required), maxResults, includeLayout, shortPath, +2 more.

get_appsA

List currently connected React Native apps and their connection status. If no apps are connected, run scan_metro first to establish a connection.

Inputs: no named parameters.

get_bundle_errorsA

Retrieve captured Metro bundling/compilation errors. These are errors that occur during the bundle build process (import resolution, syntax errors, transform errors) that prevent the app from loading. If no errors are captured but Metro is running without connected apps, automatically falls back to screenshot+OCR to capture the error from the device screen.

Inputs: maxErrors, platform, deviceId.

get_bundle_statusA

Get the current Metro bundler status including build state and any recent bundling errors. Use this to check if there are compilation/bundling errors that prevent the app from loading.

Inputs: no named parameters.

get_component_treeA

Get the React component tree from the running app. RECOMMENDED: Use focusedOnly=true with structureOnly=true for a token-efficient overview of just the active screen (~1-2KB). This skips navigation wrappers and global overlays, showing only what's actually visible.

Inputs: focusedOnly, structureOnly, maxDepth, includeProps, +3 more.

get_connection_statusA

Get detailed connection health status including uptime, recent disconnects/reconnects, and connection gaps that may indicate missing data.

Inputs: no named parameters.

get_debug_serverA

Get the debug HTTP server URL. Use this to find where you can access logs, network requests, and other debug data via HTTP.

Inputs: no named parameters.

get_inspector_selectionA

Get the React component at coordinates or read the current Element Inspector selection. If x/y provided: auto-enables inspector, taps at coordinates, returns component hierarchy. If no coordinates: returns current selection. Works in all React Native versions including Fabric.

Inputs: x, y.

get_logsA

Retrieve console logs from connected React Native app. Tip: Use summary=true first for a quick overview (counts by level + last 5 messages), then fetch specific logs as needed.

Inputs: maxLogs, level, startFromText, maxMessageLength, +3 more.

get_network_requestsA

Retrieve captured network requests from connected React Native app. Shows URL, method, status, and timing. Tip: Use summary=true first for stats overview (counts by method, status, domain), then fetch specific requests as needed.

Inputs: maxRequests, method, urlPattern, status, +2 more.

get_network_statsB

Get statistics about captured network requests: counts by method, status code, and domain.

Inputs: no named parameters.

get_request_detailsA

Get full details of a specific network request including headers, body, and timing. Use get_network_requests first to find the request ID.

Inputs: requestId (required), maxBodyLength, verbose.

get_screen_layoutA

Get layout information for all components on screen. USE AFTER get_component_tree: First use get_component_tree(structureOnly=true) to understand structure, then use this tool OR find_components with includeLayout=true to get layout details for specific areas. This tool returns full layout data which can be large for complex screens.

Inputs: maxDepth, componentsOnly, shortPath, summary, +1 more.

inspect_at_pointA

Inspect the React component at specific (x, y) coordinates. Works like React Native's Element Inspector. NOTE: This API (getInspectorDataForViewAtPoint) may not be available in newer React Native versions with Fabric. If unavailable, use ios_describe_point/android_describe_point for native element info, then find_components to locate the React component.

Inputs: x (required), y (required), includeProps, includeFrame.

inspect_componentA

Inspect a specific React component by name. DRILL-DOWN TOOL: Use after get_component_tree(structureOnly=true) to inspect specific components. Returns props, style, state (hooks), and optionally children tree. Use childrenDepth to control how deep nested children go.

Inputs: componentName (required), index, includeState, includeChildren, +3 more.

inspect_globalA

Inspect a global object to see its properties, types, and whether they are callable functions. Use this BEFORE calling methods on unfamiliar objects to avoid errors.

Inputs: objectName (required).

ios_boot_simulatorA

Boot an iOS simulator by UDID. Use list_ios_simulators to find available simulators.

Inputs: udid (required).

ios_buttonA

Press a hardware button on an iOS simulator. Requires IDB to be installed (brew install idb-companion).

Inputs: button (required), duration, udid.

ios_describe_allA

Get accessibility information for the entire iOS simulator screen. Returns a nested tree of UI elements with labels, values, and frames. Requires IDB to be installed (brew install idb-companion).

Inputs: udid.

ios_describe_pointA

Get accessibility information for the UI element at a specific point on the iOS simulator screen. Requires IDB to be installed (brew install idb-companion).

Inputs: x (required), y (required), udid.

ios_find_elementA

Find a UI element on iOS simulator by accessibility label or value. Returns element details including tap coordinates. Requires IDB (brew install idb-companion). Workflow: 1) wait_for_element, 2) find_element, 3) tap with returned coordinates. Prefer this over screenshots for button taps.

Inputs: label, labelContains, value, valueContains, +3 more.

ios_input_textA

Type text into the active input field on an iOS simulator. Requires IDB to be installed (brew install idb-companion).

Inputs: text (required), udid.

ios_install_appB

Install an app bundle (.app) on an iOS simulator

Inputs: appPath (required), udid.

ios_key_eventA

Send a key event to an iOS simulator by keycode. Requires IDB to be installed (brew install idb-companion).

Inputs: keycode (required), duration, udid.

ios_key_sequenceB

Send a sequence of key events to an iOS simulator. Requires IDB to be installed (brew install idb-companion).

Inputs: keycodes (required), udid.

ios_launch_appB

Launch an app on an iOS simulator by bundle ID

Inputs: bundleId (required), udid.

ios_open_urlA

Open a URL in the iOS simulator (opens in default handler or Safari)

Inputs: url (required), udid.

ios_screenshotB

Take a screenshot from an iOS simulator. Returns the image data that can be displayed.

Inputs: outputPath, udid.

ios_swipeB

Swipe gesture on an iOS simulator screen. Requires IDB to be installed (brew install idb-companion).

Inputs: startX (required), startY (required), endX (required), endY (required), +3 more.

ios_tapA

Tap at specific coordinates on an iOS simulator screen. WORKFLOW: Use ocr_screenshot first to get tap coordinates, then use this tool with the returned tapX/tapY values. Requires IDB (brew install idb-companion).

Inputs: x (required), y (required), duration, udid.

ios_tap_elementA

Tap an element by its accessibility label. Requires IDB (brew install idb-companion). TIP: Consider using ocr_screenshot first - it returns ready-to-use tap coordinates for all visible text and works without requiring accessibility labels.

Inputs: label, labelContains, index, duration, +1 more.

ios_terminate_appB

Terminate a running app on an iOS simulator

Inputs: bundleId (required), udid.

ios_wait_for_elementA

Wait for a UI element to appear on iOS simulator. Polls until found or timeout. Requires IDB (brew install idb-companion). Use this FIRST after navigation to ensure screen is ready, then use find_element + tap.

Inputs: label, labelContains, value, valueContains, +5 more.

list_android_devicesB

List connected Android devices and emulators via ADB

Inputs: no named parameters.

list_debug_globalsA

List globally available debugging objects in the connected React Native app (Apollo Client, Redux store, React DevTools, etc.). Use this to discover what state management and debugging tools are available.

Inputs: no named parameters.

list_ios_simulatorsC

List available iOS simulators

Inputs: onlyBooted.

ocr_screenshotA

RECOMMENDED: Use this tool FIRST when you need to find and tap UI elements. Takes a screenshot and extracts all visible text with tap-ready coordinates using OCR. ADVANTAGES over accessibility trees: (1) Works on ANY visible text regardless of accessibility labels, (2) Returns ready-to-use tapX/tapY coordinates - no conversion needed, (3) Faster than parsing accessibility hierarchies, (4) Works consistently across iOS and Android. USE THIS FOR: Finding buttons, labels, menu items, tab bars, or any text you need to tap. Simply find the text in the results and use its tapX/tapY with the tap command.

Inputs: platform (required), deviceId.

reload_appA

Reload the React Native app (triggers JavaScript bundle reload like pressing 'r' in Metro). Will auto-connect to Metro if no connection exists. IMPORTANT: React Native has Fast Refresh enabled by default - code changes are automatically applied without needing reload. Only use when: (1) logs/behavior don't reflect code changes after a few seconds, (2) app is in broken/error state, or (3) need to reset app state completely (navigation stack, context, etc.).

Inputs: no named parameters.

restart_http_serverA

Note: HTTP server now runs in-process to share state. To apply code changes, restart the MCP session.

Inputs: no named parameters.

scan_metroA

Scan for running Metro bundler servers and automatically connect to any found React Native apps. This is typically the FIRST tool to call when starting a debugging session - it establishes the connection needed for other tools like get_logs, execute_in_app, and reload_app.

Inputs: startPort, endPort.

search_logsC

Search console logs for text (case-insensitive)

Inputs: text (required), maxResults, maxMessageLength, verbose, +1 more.

search_networkC

Search network requests by URL pattern (case-insensitive)

Inputs: urlPattern (required), maxResults, format.

toggle_element_inspectorA

Toggle React Native's Element Inspector overlay programmatically. This is the same as manually doing: Dev Menu > Toggle Element Inspector. Useful for enabling inspector features without user interaction.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 64 tools

    Disambiguation3/5

    The tool set has clear groupings (Android, iOS, React Native debugging, Metro connection, etc.) with distinct purposes within each group, but there is significant overlap between similar tools across platforms (e.g., android_describe_all and ios_describe_all) and between alternative methods (e.g., ocr_screenshot vs. accessibility-based tools). Descriptions help clarify, but agents may struggle to choose between overlapping options without deep domain knowledge.

    Naming Consistency4/5

    Tool names follow a consistent snake_case pattern throughout, with clear verb_noun structures (e.g., android_tap, get_logs, scan_metro). Minor deviations exist, such as ocr_screenshot using an acronym prefix and some tools having longer names (e.g., toggle_element_inspector), but the overall naming is predictable and readable.

    Tool Count2/5

    With 64 tools, the count is excessive for a single server, making it overwhelming and difficult to navigate. While the domain (React Native debugging with Android/iOS support) is broad, many tools are redundant or highly specialized, leading to a bloated interface that could be streamlined without losing functionality.

    Completeness5/5

    The tool set provides comprehensive coverage for React Native debugging, including connection management, log retrieval, network monitoring, component inspection, and device interaction for both Android and iOS. It supports full CRUD-like operations (e.g., install/launch/terminate apps, input text, swipe/tap) and handles edge cases like error recovery and OCR alternatives, leaving no obvious gaps for the intended purpose.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • F
      license
      Not graded
      quality
      Not graded
      maintenance
      Captures and stores console output from any process in SQLite with full-text search, enabling AI assistants to search logs, monitor errors, and analyze multi-process activity through natural language queries.
      -
    • A
      license
      Not graded
      quality
      D
      maintenance
      Bridges React Native DevTools, enabling AI assistants to debug, profile, and inspect React Native applications through a standardized protocol.
      4
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      An MCP server for tailing Re.Pack/Rspack dev server logs. Enables AI assistants to query build logs, find errors, and monitor compilation status.
      5
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Captures browser console messages (log, warn, error, etc.) and makes them available to AI language models like Claude Code and Gemini CLI for seamless debugging and development.
      4
      104 npm
      MIT