Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
Nothing to run from here
Rn Devtools is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
5
downloads a day
local
runs on your machine
363
downloads in 30d
What it does
MCP server for React Native runtime debugging — zero-config access to Redux state, AsyncStorage, actions, logs, network, and profiling from your running app
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user rn-devtools-mcp '--' npx -y mcp-rn-devtools
# 2 — ask your agent for something these tools do
# clear_buffers, dispatch_action, evaluate_js and 22 more
Rn Devtools costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
PAAll 2 servers
pablonortiz2 servers
2 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Rn Devtools as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user rn-devtools-mcp '--' npx -y mcp-rn-devtoolsReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
25 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Clear captured data buffers (logs, errors, network, actions, state, renders). Call before reproducing a bug so subsequent reads contain only fresh data.
No parameter schema on file.
Dispatch a Redux action to a store discovered by the runtime agent. Useful to reproduce states or trigger flows while debugging.
No parameter schema on file.
Execute JavaScript in the React Native app context via CDP Runtime.evaluate. Use for inspecting state, refs, timers, or any runtime value. Expression runs in the global scope of the Hermes JS engine.
No parameter schema on file.
Force garbage collection and return before/after heap memory comparison.
No parameter schema on file.
Get Redux action dispatch log. Shows action types, reducer duration, and which state slices changed. Zero-config: the runtime agent records dispatches automatically once a store is discovered.
No parameter schema on file.
Get application state from Redux/Zustand stores. Zero-config: discovers Redux stores automatically via the injected runtime agent. The optional SDK adds Zustand and custom stores.
No parameter schema on file.
Get console log output from the running React Native app. Returns log, info, and debug messages (not errors/warnings — use get_errors and get_warnings for those).
No parameter schema on file.
Profile CPU usage for a given duration and return the hottest functions sorted by self time.
No parameter schema on file.
Get JavaScript errors and exceptions from the running React Native app. Includes RedBox errors captured via console.error.
No parameter schema on file.
Get failed HTTP requests (status >= 400 or network errors) from the running React Native app.
No parameter schema on file.
Get current JavaScript heap memory usage from the React Native app.
No parameter schema on file.
Get the current navigation state (React Navigation). Zero-config: the runtime agent discovers the navigation container automatically; the SDK channel is used when available.
No parameter schema on file.
Get navigation transition timing data — how long each screen transition takes. Requires mcp-rn-devtools-sdk with navigationRef.
No parameter schema on file.
Get HTTP network requests from the running React Native app. Shows URL, method, status and duration; verbose mode adds headers and truncated bodies (secrets redacted).
No parameter schema on file.
Get component render profile data. Requires mcp-rn-devtools-sdk with Profiler wrapping components.
No parameter schema on file.
Show what changed in a Redux store since the last call. First call records a baseline; subsequent calls diff the current state against it and reset the baseline. Workflow: call once, interact with the app (or dispatch), call again.
No parameter schema on file.
List storage keys from AsyncStorage or MMKV. AsyncStorage works zero-config via the runtime agent; MMKV requires the SDK.
No parameter schema on file.
Read a value from AsyncStorage or MMKV by key. AsyncStorage works zero-config via the runtime agent; MMKV requires the SDK. Secrets are redacted (opt out with MCP_RN_NO_REDACT=1).
No parameter schema on file.
Get LogBox warnings from the running React Native app. These are captured via console.warn.
No parameter schema on file.
Check connection status and diagnose problems: CDP/SDK channels, discovered stores, error/request counts, and actionable hints when something is not connected.
No parameter schema on file.
Resolve a bundle line/column (e.g. from a CPU profile or stack trace showing index.bundle:69306) back to the original source file and line. Requires Metro to be running.
No parameter schema on file.
Take a heap snapshot and return a summary with top memory retainers. This may take a few seconds.
No parameter schema on file.
List debuggable React Native targets registered with Metro (multiple devices/apps can be connected). Shows which one the server is using.
No parameter schema on file.
Connect to a specific debug target by ID (from list_targets) and pin it for reconnects. Use when multiple devices or apps are connected to Metro.
No parameter schema on file.
Block until a console log or error matching a pattern appears (only entries newer than the call count). Use it to synchronize with app activity: call it, interact with the app, and it returns the moment the log shows up.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Rn Devtools or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 0.5.1 · scanned 15 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings1 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digestec4e9ab9e21b1da360879f5cd0f0ee560d13171db3c5cc318bd95a233488d390
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (25 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_console_logs | no tags | |
| get_errors | no tags | |
| get_warnings | no tags | |
| get_network_requests | no tags | |
| get_failed_requests | no tags | |
| health_check | no tags | |
| get_navigation_state | no tags | |
| get_memory_usage | no tags | |
| take_heap_snapshot | no tags | |
| get_cpu_profile | no tags | |
| force_gc | no tags | |
| get_render_profile | no tags | |
| get_app_state | no tags | |
| get_storage_keys | no tags | |
| get_storage_value | no tags | |
| evaluate_js | no tags | |
| resolve_source_location | no tags | |
| get_action_log | no tags | |
| get_navigation_timing | no tags | |
| dispatch_action | no tags | |
| clear_buffers | no tags | |
| wait_for_log | no tags | |
| get_state_diff | no tags | |
| list_targets | no tags | |
| select_target | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestec4e9ab9e21b1da3
Scanned2026-10-15
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.5.1. Pin a release below and the command asks for exactly that one.
0.5.1
5 Oct 2026
latestNo release note was published with this version.
0.5.0
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Rn Devtools can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.