Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

rn-devtools-hub

NPM · RN-DEVTOOLS-HUB · SCANNED SEP 24

Drive a running React Native or Expo app from inside its JS runtime: see, act, prove.

Available components

0 this week 81 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency45
Schema Quality & AI Usability77
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 6379 tokens (~92/item across 69 items; 69 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management87
  • Stability observed for 26 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage76
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 29% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 4 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 70 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the rn-devtools-hub MCP server?

rn-devtools-hub runs locally as an npm package, launched with npx -y rn-devtools-hub. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · rn-devtools-hub

# add to Claude Code
claude mcp add rn-devtools-hub-rn-devtools-hub -- npx -y rn-devtools-hub
// .cursor/mcp.json
{
  "mcpServers": {
    "rn-devtools-hub-rn-devtools-hub": {
      "command": "npx",
      "args": [
        "-y",
        "rn-devtools-hub"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "rn-devtools-hub-rn-devtools-hub": {
      "command": "npx",
      "args": [
        "-y",
        "rn-devtools-hub"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add rn-devtools-hub-rn-devtools-hub -- npx -y rn-devtools-hub
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "rn-devtools-hub-rn-devtools-hub": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "rn-devtools-hub"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add rn-devtools-hub-rn-devtools-hub --command npx --arg -y --arg rn-devtools-hub
# ~/.hermes/config.yaml
mcp_servers:
  rn-devtools-hub-rn-devtools-hub:
    command: "npx"
    args: ["-y", "rn-devtools-hub"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "rn-devtools-hub-rn-devtools-hub": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "rn-devtools-hub"
      ]
    }
  }
}
# add to Vellum
assistant mcp add rn-devtools-hub-rn-devtools-hub -t stdio -c npx -a -y rn-devtools-hub
// mcp.json
{
  "mcpServers": {
    "rn-devtools-hub-rn-devtools-hub": {
      "command": "npx",
      "args": [
        "-y",
        "rn-devtools-hub"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 23 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 22 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 21 Sept 26 0
    • Stability: 0.97 → pass security
  • 20 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Sept 26 −3
    • Stability: pass → 0.80 functional
  • 14 Sept 26 0
    • Stability: 0.97 → pass security
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 24 Sept 2026 · Analysed npm/rn-devtools-hub@0.22.0

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 69 exposed · ~6,189 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
advance_time ~56

Moves the frozen clock forward by ms. It moves the clock, it does NOT fire pending timers: driving the scheduler would mean replacing setTimeout under a running app.

NameTypeReqDescription
deviceIdstring
msintegeryes

No output schema declared.

No examples provided.

assert ~428

Checks runtime evidence. network_response RETRIES until timeoutMs for an observed response matching required urlContains, method and status; mocked responses require allowMocked:true. Success carries the response evidence. network_ok means only no observed network error, never that a request completed. Negative event assertions require current capture coverage; unavailable coverage returns ok:false, conclusive:false. no_crash covers captured JS errors and rejections, not native crashes. Element kinds (visible, absent, text, count) retry until timeoutMs. Scope events with since from before the action, or windowMs; settleMs delays negative checks.

NameTypeReqDescription
allowMockedbooleannetwork_response: accept instrumented mocked responses (default false)
bystring
deviceIdstring
equalsintegerkind:count, the exact number of matching elements expected
exactboolean
ignorearraykind:no_console_error, substrings to tolerate
includeHiddenboolean
kindstringyes
maxintegerkind:count, highest acceptable number of matches
methodstringnetwork_response: required HTTP method
minintegerkind:count, lowest acceptable number of matches
namestringAccessible name filter, used with by:role
settleMsintegerEvent kinds: wait before judging, to let in-flight requests land
sinceintegerEvent kinds: judge everything after this cursor
statusintegernetwork_response: required response status
textstringkind:text, the expected text when it differs from value
timeoutMsintegerElement kinds and network_response: retry deadline (default 5000, 0 checks once)
urlContainsstringNetwork assertions: URL substring, required for network_response
valuestring
windowMsintegerEvent kinds: trailing window when no cursor is given (default 5000)
withinobject

No output schema declared.

No examples provided.

audit_accessibility ~88

Compares what React renders with what the OS exposes and reports the DIFFERENCE: pressables with no accessible name, and text or controls missing from the accessibility tree. A tool with only the accessibility tree cannot find what is missing from it. Returns conclusive:false rather than a clean report when either tree came back empty.

NameTypeReqDescription
deviceIdstring
targetstring

No output schema declared.

No examples provided.

boot_device ~43

Boots an iOS simulator by target id (sim:<udid>) and opens the Simulator app. Android emulators must be started externally.

NameTypeReqDescription
targetstringyes

No output schema declared.

No examples provided.

build_app ~143

Builds the app by delegating to expo run:ios, expo run:android or eas build, and streams the build's failures onto the SAME timestamped bus as the crashes and the requests. Compile error at t0, relaunch at t1, first JS crash at t2, one clock: the agent reads a continuous stream from broken code to running app. xcodebuild and gradle are delegated to, never reimplemented.

NameTypeReqDescription
devicestringTarget device or simulator name for the local runner
platformstringyes
profilestringeas.json profile; given, the build goes through EAS instead of the local runner

No output schema declared.

No examples provided.

capture_store_screenshots ~230

Captures the App Store and Play Store screenshots from the running app, driven by a manifest (devices from list_targets, locales, screens). Each screen is reached with the app's own dev actions (nav:*, seed:*, auth:*) and waited on with an event rather than a sleep, so the same set can be regenerated identically next release. Files are written to disk at the device's native resolution and NOTHING is resized: the answer is a manifest of paths and sizes, never the images, so this costs no context. Reports the sizes it does not recognise instead of uploading them as the wrong device class. Upload with asc_upload_screenshots and gplay_upload_screenshots.

NameTypeReqDescription
devicestringOnly this device label or target from the manifest
deviceIdstring
localestringOnly this locale from the manifest
manifestobjectThe manifest itself; read from .rn-devtools/store-screenshots.json when absent
screenstringOnly this screen from the manifest, to iterate on one

No output schema declared.

No examples provided.

compare_snapshot ~125

Compares the current screen with a named baseline and EXPLAINS the difference: the changed ratio, the bounding box, the component that owns that region with its source file and line, and what the event bus recorded since the baseline. A percentage alone says something moved; this says what to edit.

NameTypeReqDescription
deviceIdstring
maxRationumberTolerated changed-pixel ratio (default 0.001)
namestringyes
targetstring
withImagebooleanReturn the diff image as well

No output schema declared.

No examples provided.

export_flow ~77

Exports runtime actions and subsequent observed events. attribution:temporal means ordering, not proven causality; review background traffic before using the recording as a test. format:mcp returns replay calls, text a readable script, json the structure. Recorded failures make clean:false.

NameTypeReqDescription
deviceIdstring
formatstring

No output schema declared.

No examples provided.

export_session ~101

Exports one session as a single correlated artifact: network, console, crashes, navigation and UI changes on ONE timeline relative to the session start, plus the crash, failed-request and console-error sections an investigation opens first. Omit sessionId for the most recent session. format:"markdown" pastes into a GitHub issue as it is; format:"json" is for further processing.

NameTypeReqDescription
formatstring
sessionIdstring

No output schema declared.

No examples provided.

freeze_time ~80

Freezes the app's JS clock at an ISO instant (or now), so relative dates and time-dependent rendering stop drifting between runs. Deterministic at the JS level only: Date, new Date() and Date.now(). Native animations and Reanimated read native clocks and are unaffected.

NameTypeReqDescription
deviceIdstring
isostring

No output schema declared.

No examples provided.

get_accessibility_tree ~89

Reads the accessibility tree the OS exposes, which is what assistive technology and any external automation see. Works when the React runtime cannot be reached (release build, WebView, native screen, splash). Android uses uiautomator; iOS needs AXe installed. Every node carries source:"accessibility" so it is never confused with a React node.

NameTypeReqDescription
targetstring

No output schema declared.

No examples provided.

get_app_info ~31

Returns app, device, OS, development mode and network connection information.

NameTypeReqDescription
deviceIdstring

No output schema declared.

No examples provided.

get_capabilities ~34

Reports what the selected app attached and the exact SDK call that enables each missing capability.

NameTypeReqDescription
deviceIdstring

No output schema declared.

No examples provided.

get_crashes ~32

Returns recent crashes and unhandled errors.

NameTypeReqDescription
deviceIdstring
limitinteger

No output schema declared.

No examples provided.

get_endpoint_stats ~61

Computes calls, errors and p50/p95 latencies per endpoint from the captured requests. With nothing captured it returns {endpoints: [], capture} instead, where capture says whether the network is instrumented at all.

NameTypeReqDescription
deviceIdstring

No output schema declared.

No examples provided.

get_events_since ~83

Returns device events after a cursor (monotonic seq). Poll with the returned cursor to follow network, console, crash, nav, screen.ready and ui.change without missing anything. Omit cursor for the most recent events.

NameTypeReqDescription
cursorinteger
deviceIdstring
limitinteger
typesarray

No output schema declared.

No examples provided.

get_flow ~26

Reads and validates one project-relative .hubflow scenario.

NameTypeReqDescription
pathstringyes

No output schema declared.

No examples provided.

get_logs ~58

Returns captured JavaScript console entries filtered by level, text and cursor.

NameTypeReqDescription
containsstring
deviceIdstring
levelstring
limitinteger
sinceinteger

No output schema declared.

No examples provided.

get_native_logs ~169

Native device logs the JS console cannot see, with looping duplicates collapsed. Android: bounded logcat dump, fast (filter by app package via process). iOS: unified log dump of the last sinceMinutes (default 1); SLOW, roughly 10-30 s per minute of window, so keep the window small and filter by process. Catches crashes before the bundle loads and dev-client startup issues.

NameTypeReqDescription
filterstringSubstring filter on the log lines
linesinteger
processstringAndroid: app package (pid filter). iOS: process name
sinceMinutesinteger
targetstringsim:<udid> or adb:<serial> from list_targets; omitted = the single booted target

No output schema declared.

No examples provided.

get_orientation ~43

Reads the current rotation (Android).

NameTypeReqDescription
targetstringsim:<udid> or adb:<serial> from list_targets; omitted = the single booted target

No output schema declared.

No examples provided.

get_overlay ~37

Says whether the expo-dev-menu floating button is currently shown, and returns the dev-menu preferences behind it.

NameTypeReqDescription
deviceIdstring

No output schema declared.

No examples provided.

get_project_context ~95

Returns what the project DECLARES (installed versions, Expo SDK, New Architecture, JS engine, plugins), what the app ACTUALLY runs (engine, Fabric, bridgeless, TurboModules, native React Native version, mounted React renderer), and the contradictions between the two. The divergence block catches stale native builds, Expo Go running a plugin project and release bundles before any other debugging.

NameTypeReqDescription
deviceIdstring

No output schema declared.

No examples provided.

get_recent_network ~41

Returns recent network events and explains whether an empty result means quiet traffic or missing instrumentation.

NameTypeReqDescription
deviceIdstring
limitinteger

No output schema declared.

No examples provided.

get_state ~80

Reads a store the app registered with devtools.registerStore (Zustand, Redux, React Query or a custom adapter). Omit store to list what is available. path drills in with dots; for React Query it is the JSON query key.

NameTypeReqDescription
deviceIdstring
pathstring
storestring

No output schema declared.

No examples provided.

get_ui_tree ~119

Returns the visible React semantic tree with props, measured rectangles and source locations. Requires attachUiAutomation.

NameTypeReqDescription
deviceIdstring
includeHiddenboolean
includeSourcebooleanAttach the source location to every node (default true); set false to shrink the payload
maxDepthinteger
maxNodesinteger
metroUrlstringMetro server used to map bundle positions back to source (default: read from the stack, else http://localhost:8081)

No output schema declared.

No examples provided.

install_app ~72

Installs an app bundle on the target (simctl install / adb install -r).

NameTypeReqDescription
pathstringyesPath to the .app, .ipa or .apk
targetstringsim:<udid> or adb:<serial> from list_targets; omitted = the single booted target

No output schema declared.

No examples provided.

launch_app ~245

Launches the app with zero dialogs and nothing floating over the screen. iOS: simctl launch with --initialUrl (dev-client loads the given Metro URL directly, no deep link). Android: explicit-component am start with the URL as VIEW data. coldStart terminates first; the expo dev-menu onboarding is skipped automatically, and its floating action button is hidden (iOS), because it sits in its own window, is therefore invisible to get_ui_tree, and swallows taps meant for the buttons underneath it.

NameTypeReqDescription
appIdstringyes
coldStartboolean
hideDevMenuFabbooleaniOS: hide the expo-dev-menu floating bubble, which covers the bottom-right corner and intercepts taps (default true). Pass false to put it back. On Android the equivalent is a manifest meta-data, so…
suppressDevMenuIntroboolean
targetstringsim:<udid> or adb:<serial> from list_targets; omitted = the single booted target
urlstringMetro server URL (http://host:8081) or deep link

No output schema declared.

No examples provided.

list_actions ~60

Lists the dev actions the app registered (name, label, description, argsSchema, danger). Conventions: nav:* navigate directly to a screen, auth:* instant sessions, seed:* fixtures, reset:* deterministic state.

NameTypeReqDescription
deviceIdstring

No output schema declared.

No examples provided.

list_devices ~22

Lists the React Native devices known to the hub and their connection state.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_flows ~26

Lists versioned .hubflow scenarios in tests/hub with their latest local run.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_plugins ~124

Lists the hub plugins, which reach the services around the app rather than the app itself (App Store Connect, Google Play). For each one: whether it is configured, which tools it exposes, which of them CHANGE something (writeTools) and whether writes are enabled, the exact configuration keys still missing and where to set them, and every host it will contact. A plugin with no credentials exposes no tool at all, so this is the only place its tools are visible before it is set up. Credentials are never returned, only whether they are set and where they came from.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_previews ~37

Lists the components the app registered with devtools.registerPreview, and whether the preview outlet is mounted.

NameTypeReqDescription
deviceIdstring

No output schema declared.

No examples provided.

list_sessions ~40

Lists the persisted sessions, most recent first. Sessions survive hub restarts and app reloads, so an investigation can start long after the run it is about.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_targets ~50

Lists OS-level targets: iOS simulators (simctl) and Android devices/emulators (adb), with their boot state. Native tools take these targets, distinct from the JS deviceId of list_devices.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

mock_network ~120

Controls the requests going through the instrumented fetch: rules to stub a status and a body, or a condition among normal, offline, 3g and flaky. Failures are spaced deterministically rather than randomly, so a flaky profile stays reproducible. Mocked responses are flagged on the bus so an agent never mistakes a fixture for the backend. Only covers wrapFetch; an axios instance keeps its own adapter.

NameTypeReqDescription
actionstring
conditionstring
deviceIdstring
rulesarray

No output schema declared.

No examples provided.

open_url ~82

Opens a deep link on the target (simctl openurl / am start VIEW). On Android pass appId to pin the handler and avoid the chooser.

NameTypeReqDescription
appIdstring
targetstringsim:<udid> or adb:<serial> from list_targets; omitted = the single booted target
urlstringyes

No output schema declared.

No examples provided.

propose_flow_repair ~65

Writes a sibling .candidate.hubflow for a failed target only when recorded identity evidence strongly matches a reported candidate. It never changes assertions or the original file.

NameTypeReqDescription
candidateIndexintegeryes
pathstringyes
stepIndexintegeryes

No output schema declared.

No examples provided.

query_sqlite ~37

Runs a SQLite SELECT or PRAGMA query on the connected device.

NameTypeReqDescription
deviceIdstring
sqlstringyes

No output schema declared.

No examples provided.

query_ui ~134

Finds visible elements by semantic selector and returns values, rectangles and source locations. Retries until timeoutMs.

NameTypeReqDescription
bystringyes
deviceIdstring
exactboolean
includeHiddenboolean
limitinteger
namestring
timeoutMsintegerRetry while nothing matches, up to this deadline (default 1000). A UI is asynchronous and an empty answer during a transition reads like a regression. Pass 0 for a single immediate look.
valuestringyes
withinobject

No output schema declared.

No examples provided.

render_component ~83

Mounts a registered component INSIDE the running app, under its real providers, session and cache: nothing to mock, unlike an isolated preview. Returns the measured rect and the rendered subtree. Verifying a component no longer means navigating to the screen that contains it.

NameTypeReqDescription
deviceIdstring
namestringyes
propsobject

No output schema declared.

No examples provided.

repair_adb_routes ~83

Restores adb reverse mappings lost after an emulator or USB reconnection. Defaults to Metro 8081 and the current Hub port. Omit target only when exactly one Android target is ready.

NameTypeReqDescription
portsarray
targetstringsim:<udid> or adb:<serial> from list_targets; omitted = the single booted target

No output schema declared.

No examples provided.

resolve_source ~71

Retries Metro symbolication for a source that remained via stack after the short inline budget expired. This is separate so source enrichment never delays a successful UI action.

NameTypeReqDescription
componentNamestring
metroUrlstring
stackarrayyes
timeoutMsinteger

No output schema declared.

No examples provided.

restore_time ~24

Gives the app its real clock back.

NameTypeReqDescription
deviceIdstring

No output schema declared.

No examples provided.

run_action ~71

Runs an action declared by the app with optional typed args (e.g. nav:packageDetail {id}). Discover actions and their schemas with list_actions. Dangerous actions must be confirmed in the MCP client.

NameTypeReqDescription
argsobject
deviceIdstring
namestringyes

No output schema declared.

No examples provided.

run_flow ~64

Runs a validated .hubflow with explicit expectations and writes screenshots and a human-readable report under .rn-devtools. Recorded event association is temporal, not proven causality.

NameTypeReqDescription
deviceIdstring
pathstringyes
targetstring

No output schema declared.

No examples provided.

save_flow ~60

Saves the current action and consequence recording as a versioned .hubflow file under tests/hub by default.

NameTypeReqDescription
descriptionstring
deviceIdstring
pathstringyes
screenshotPolicystring

No output schema declared.

No examples provided.

screenshot_native ~62

Pixel screenshot of the target screen (PNG), complementing get_ui_tree: the tree gives structure, this gives the actual rendering.

NameTypeReqDescription
targetstringsim:<udid> or adb:<serial> from list_targets; omitted = the single booted target

No output schema declared.

No examples provided.

send_push ~90

Simulates a remote push notification on an iOS simulator (simctl push). payload is the APNs JSON with a top-level aps key. Rendering still depends on the app having notification permission.

NameTypeReqDescription
appIdstringyes
payloadobjectyes
targetstringsim:<udid> or adb:<serial> from list_targets; omitted = the single booted target

No output schema declared.

No examples provided.

session_start ~235

One-call bootstrap and app switch: resolve target, pre-grant permissions, launch the dev build on the given Metro server, then wait for the expected app to connect. Pass appName when several runtimes share the hub so an event from the wrong app cannot satisfy the wait. Android derives the development-client scheme from app.json when scheme is omitted.

NameTypeReqDescription
adbPortsarrayAdditional adb reverse ports to restore with Metro and the hub.
appIdstringyes
appNamestringExpected devtools appName. Filters connection events when switching between apps.
coldStartboolean
hideDevMenuFabbooleaniOS: hide the expo-dev-menu floating bubble, which intercepts taps meant for the elements under it (default true)
permissionsobject
platformstringyes
schemestringAndroid development-client scheme. Defaults to app.json expo.scheme or exp+slug.
serverUrlstring
targetstring
timeoutMsinteger
waitForstring

No output schema declared.

No examples provided.

set_animations ~72

Enables or disables system animations on Android (window/transition/animator scales) for deterministic captures. Remember to re-enable at session end.

NameTypeReqDescription
enabledbooleanyes
targetstringsim:<udid> or adb:<serial> from list_targets; omitted = the single booted target

No output schema declared.

No examples provided.

Common questions

What is the rn-devtools-hub MCP server?

rn-devtools-hub is an MCP server listed in the public MCP registry as io.github.rn-devtools-hub/rn-devtools-hub. Drive a running React Native or Expo app from inside its JS runtime: see, act, prove. This page covers its npm package (rn-devtools-hub).

Is the rn-devtools-hub MCP server safe to use?

rn-devtools-hub scores 81 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 24 September 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the rn-devtools-hub MCP server expose?

rn-devtools-hub exposes 69 tools: list_devices, get_capabilities, get_app_info, get_logs, get_recent_network, and 64 more. Their descriptions and schemas cost roughly 6,189 tokens of context every time the server is loaded.

Is the rn-devtools-hub MCP server still maintained?

rn-devtools-hub is still listed as active in the MCP registry. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the rn-devtools-hub MCP server under?

rn-devtools-hub declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.