Local-first knowledge graph for token-efficient code review through MCP and CLI
Nothing to run from here
Flutter 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.
88/100
trust score
2
downloads a day
local
runs on your machine
48
downloads in 30d
What it does
MCP server that connects AI agents to running Flutter apps via the Dart VM Service for runtime inspection, profiling, and debugging
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user flutter-devtools-mcp '--' npx -y flutter-devtools-mcp
# 2 — ask your agent for something these tools do
# connect, disconnect, get_app_info and 19 more
Flutter 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
TRAll 1 server
treexi1 server
1 category
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 Flutter 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 flutter-devtools-mcp '--' npx -y flutter-devtools-mcpReconnect, 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
22 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.
Connect to a running Flutter app via its VM Service URI. The URI is printed when you run
No parameter schema on file.
Disconnect from the currently connected Flutter app.
No parameter schema on file.
Get detailed information about the connected Flutter app including VM info, isolates, and available extensions.
No parameter schema on file.
Trigger a hot reload on the running Flutter app. Injects updated source code without restarting the app or losing state.
No parameter schema on file.
Trigger a hot restart on the running Flutter app. Restarts the app from scratch but is faster than a full rebuild.
No parameter schema on file.
Capture a screenshot of the running Flutter app. Returns the screenshot as a base64-encoded PNG image.
No parameter schema on file.
Toggle the debug paint overlay on the Flutter app. Shows widget borders, padding, and alignment guides.
No parameter schema on file.
Evaluate a Dart expression in the context of the running Flutter app. Useful for inspecting runtime values, checking state, or running diagnostics.
No parameter schema on file.
Automatically discover running Flutter apps on this machine. Scans for Dart VM Service instances so you don
No parameter schema on file.
Get a memory allocation profile of the running Flutter app. Shows heap usage, top memory-consuming classes, and potential leak indicators.
No parameter schema on file.
Start capturing HTTP network traffic from the running Flutter app. After starting, use the app to trigger API calls, then call stop_network_capture to see all requests with timing, status codes, and sizes.
No parameter schema on file.
Stop capturing network traffic and get a detailed report of all HTTP requests including method, URL, status code, response time, and payload size.
No parameter schema on file.
No parameter schema on file.
Start a performance profiling session. After starting, interact with the app (scroll, tap, navigate) to generate activity, then call stop_profiling to get the analysis. The app should be running in profile mode (
No parameter schema on file.
Stop the current profiling session and get a detailed performance analysis including frame timing, jank detection, CPU hotspots, build/layout/paint phase analysis, and actionable recommendations.
No parameter schema on file.
Start tracking which widgets are rebuilding and how often. After starting, interact with the app, then call stop_tracking_rebuilds to see exactly which widgets rebuilt, how many times, and where they are in your code. This is the most effective way to find unnecessary rebuilds.
No parameter schema on file.
Stop tracking widget rebuilds and get a detailed report showing exactly which widgets rebuilt, how many times, and their source file locations. Sorted by rebuild count to highlight the most problematic widgets.
No parameter schema on file.
Save a named memory snapshot for later comparison. Take a snapshot before making a code change, then take another after to see the impact. Use compare_snapshots to see the diff.
No parameter schema on file.
Compare two previously saved memory snapshots to see what changed. Shows heap usage diff, which classes grew or shrank, new allocations, and freed memory. Perfect for validating that a fix actually reduced memory usage.
No parameter schema on file.
List all saved memory snapshots available for comparison.
No parameter schema on file.
Get the current widget tree of the running Flutter app. Returns a structured representation of all widgets on screen. Widgets marked with ★ are from your project code (not framework widgets).
No parameter schema on file.
Get detailed information about a specific widget by its ID (obtained from get_widget_tree). Returns render details, constraints, size, and state.
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 Flutter 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: —
BTrust score 88 / 100
Release 0.3.2 · scanned 14 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 score94
Client score88
Findings3 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digesta5bb1eb1239c73aa5b05b0a5b446c6efe109a223924bdb0bcabd9e4a8aacc002
Score vectorthreat 94 → client 88
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| 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 (22 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 |
|---|---|---|
| connect | no tags | |
| disconnect | no tags | |
| get_app_info | no tags | |
| hot_reload | no tags | |
| hot_restart | no tags | |
| take_screenshot | no tags | |
| toggle_debug_paint | no tags | |
| evaluate_expression | no tags | |
| discover_apps | no tags | |
| get_memory_snapshot | no tags | |
| start_network_capture | no tags | |
| stop_network_capture | external-sink | external-sink: keyword "http_request" |
| collect_performance_session | no tags | |
| start_profiling | no tags | |
| stop_profiling | no tags | |
| start_tracking_rebuilds | no tags | |
| stop_tracking_rebuilds | no tags | |
| save_snapshot | no tags | |
| compare_snapshots | no tags | |
| list_snapshots | no tags | |
| get_widget_tree | no tags | |
| inspect_widget | 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 digesta5bb1eb1239c73aa
Scanned2026-10-14
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 0.3.2. Pin a release below and the command asks for exactly that one.
0.3.2
undated
latestNo release note was published with this version.
—
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 Flutter 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.