Local MCP capabilities provider for Expo
Nothing to run from here
FlyTrap 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.
97/100
trust score
18
downloads a day
local
runs on your machine
894
downloads in 30d
What it does
FlyTrap mobile QA results for agents: bugs with evidence, screen graphs, network hosts, SDKs, diffs.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user flytrap-mcp '--' npx -y @flytrap-qa/mcp
# 2 — ask your agent for something these tools do
# lookup_app, get_app_profile, lookup_sdk and 19 more
FlyTrap costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
FQAll 1 server
flytrap-qa1 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 FlyTrap 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 flytrap-mcp '--' npx -y @flytrap-qa/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 — some of its tools take a key of its publisher’s own, and the rest work without.
What it asks of you
Nothing is required, but it can take FLYTRAP_API_KEY (FlyTrap API key (ft_live_...) from https://dashboard.flytrap.dev/settings/api-keys. Optional: public catalog tools work without it.) if you want to set it. Its publisher says some of its tools need it, and the rest work without.
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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Search the public FlyTrap catalog of crawled store apps by name or package id.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | App name or package id substring, e.g. "booking" or "com.booking" |
| platform | string | no | — |
| sdk | string | no | Comma-separated SDK ids the app must contain, e.g. "firebase-analytics,adjust" |
| permission | string | no | Comma-separated permission ids the app must declare |
| limit | integer | no | — |
Detected SDKs, declared permissions, labels, framework and a crawl-derived summary for one app
| Parameter | Type | Required | Notes |
|---|---|---|---|
| package_name | string | yes | Android package id or iOS bundle id, e.g. "com.booking" |
Find SDK ids by name or vendor (e.g. "adjust", "google", "ads"). Use the id with lookup_app or
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | no | Substring of SDK id, name, vendor or category; omit to list categories |
| limit | integer | no | — |
Explain a permission id or find permissions by keyword (e.g. "location", "camera"). No API key needed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Permission id or keyword, e.g. "android.permission.CAMERA" or "location" |
| limit | integer | no | — |
Confirms which FlyTrap account the configured API key belongs to. Requires FLYTRAP_API_KEY.
No parameter schema on file.
Projects (apps) the API key owner can read, with the selected crawl run for each.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | no | Case-insensitive substring of name or package_name |
| platform | string | no | — |
| limit | integer | no | — |
| offset | integer | no | — |
One project with its pipeline status and the latest crawl state. Requires FLYTRAP_API_KEY.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | FlyTrap project id (from list_projects) |
Builds (versions) registered for a project, with binary digests and which build is current.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | FlyTrap project id (from list_projects) |
One-screen summary of the selected crawl run: version, size, SDK and permission counts,
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | FlyTrap project id (from list_projects) |
Third-party SDKs detected in the selected build (with confidence and evidence sources) plus
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | FlyTrap project id (from list_projects) |
Bugs FlyTrap found in the selected crawl run, sorted by severity. Each has an id for
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | FlyTrap project id (from list_projects) |
| status | string | no | — |
| severity | string | no | — |
| limit | integer | no | — |
| offset | integer | no | — |
Everything FlyTrap recorded for one bug: the test scenario and failed step, screenshots and
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | FlyTrap project id (from list_projects) |
| bug_id | string | yes | Bug id from list_bugs, e.g. "BUG-102" |
Screens the crawler reached in the selected run and the tap edges between them
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | FlyTrap project id (from list_projects) |
Hosts the app talked to during the crawl with call counts, bytes and error rates, plus
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | FlyTrap project id (from list_projects) |
| limit | integer | no | — |
Diff two builds of the same project: SDKs, permissions, deep links, network hosts, bugs and
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | FlyTrap project id (from list_projects) |
| base_build_id | integer | yes | Older build id (from list_builds) |
| head_build_id | integer | yes | Newer build id |
Semantic search over FlyTrap's crawled feature index: describe the app you want
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Plain-language description of the wanted app |
| platform | string | no | — |
| limit | integer | no | — |
Names the features in the project's build and finds the same feature in public apps FlyTrap
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | FlyTrap project id (from list_projects) |
| match | string | no | — |
| limit | integer | no | Apps to compare against |
Competitors pinned to a project. They always lead the UX benchmark (get_ux_benchmark).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | FlyTrap project id (from list_projects) |
Searches two places: public FlyTrap projects that already have a crawled feature catalog
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | FlyTrap project id (from list_projects) |
| q | string | yes | App name or package id, e.g. "revolut" |
| limit | integer | no | — |
Pins an app to the project's UX benchmark. Give competitor_project_id for an app from
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | FlyTrap project id (from list_projects) |
| competitor_project_id | integer | no | Existing public FlyTrap project |
| package_name | string | no | Google Play package id, e.g. com.revolut.revolut |
| name | string | no | Display name for a newly created store project |
| confirm | boolean | no | Required (true) when package_name would create a new project |
Removes a pinned competitor from the project's UX benchmark. The competitor project itself is kept. Needs the "crawl" scope.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | FlyTrap project id (from list_projects) |
| competitor_project_id | integer | yes | — |
Queues a new crawl of the project's current build. This consumes crawl quota and takes
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | integer | yes | FlyTrap project id (from list_projects) |
| confirm | boolean | yes | Must be true. Confirms the user asked for a new crawl. |
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 FlyTrap 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 97 / 100
Release 0.1.4 · scanned 8 Nov 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 score97
Findings0 threat · 1 capability
Capabilitymoderate
Coveragesource
Verificationsource
Surface digest053445e15d42f7423f0b0a8326556281774ab7679fcca3932df29440f048d5d6
Score vectorthreat 100 → client 97
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| 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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| lookup_app | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_app_profile | untrusted-input | untrusted-input: keyword "crawl", declares openWorldHint: true (interacts with entities outside the server) |
| lookup_sdk | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| lookup_permission | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| whoami | no tags | |
| list_projects | untrusted-input | untrusted-input: keyword "crawl" |
| get_project | untrusted-input | untrusted-input: keyword "crawl" |
| list_builds | no tags | |
| get_build_summary | untrusted-input | untrusted-input: keyword "crawl" |
| get_sdks | no tags | |
| list_bugs | untrusted-input | untrusted-input: keyword "crawl" |
| get_bug_evidence | untrusted-input | untrusted-input: keyword "crawl" |
| get_screen_graph | no tags | |
| get_network_hosts | untrusted-input | untrusted-input: keyword "crawl" |
| compare_builds | untrusted-input | untrusted-input: keyword "crawl" |
| search_apps | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_ux_benchmark | external-sink | external-sink: handler sends an HTTP POST ( client.post('/project/projects') at src/tools/projects.js:358, handler sends an HTTP POST ( client.post(/project/projects/${project_id}/competitors) at src/tools/projects.js:368, handler sends an HTTP DELETE ( client.delete(/project/projects/${project_id}/competitors/${competitor_project_id}) at src/tools/projects.js:384 |
| list_competitors | no tags | |
| find_competitors | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| add_competitor | untrusted-inputstate-writeexternal-sink | untrusted-input: keyword "crawl"; state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( client.post('/project/projects') at src/tools/projects.js:358, handler sends an HTTP POST ( client.post(/project/projects/${project_id}/competitors) at src/tools/projects.js:368 |
| remove_competitor | state-writeexternal-sink | state-write: declares readOnlyHint: false, destructiveHint: true; external-sink: handler sends an HTTP DELETE ( client.delete(/project/projects/${project_id}/competitors/${competitor_project_id}) at src/tools/projects.js:384 |
| start_crawl | untrusted-inputstate-writeexternal-sink | untrusted-input: keyword "crawl"; state-write: declares readOnlyHint: false; external-sink: handler sends an HTTP POST ( client.post(/project/projects/${project_id}/crawl) at src/tools/projects.js:399 |
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.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest053445e15d42f742
Scanned2026-11-08
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 0.1.4. Pin a release below and the command asks for exactly that one.
0.1.4
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 FlyTrap 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.