Local MCP capabilities provider for Expo
Nothing to run from here
Ats 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.
81/100
trust score
3
downloads a day
local
runs on your machine
43
downloads in 30d
What it does
MCP server that lets LLMs drive ActionTestScript (ATS) — test automation across web, mobile, desktop, and API, powered by ats-core's REPL.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user ats-mcp '--' npx -y ats-mcp
# 2 — ask your agent for something these tools do
# start_channel, stop_channel, switch_channel and 27 more
Ats costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
ACAll 1 server
actiontestscript1 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 Ats 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 ats-mcp '--' npx -y ats-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
30 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.
Open a new ATS channel (web / mobile / desktop / api). Must be called before any action on that target.
No parameter schema on file.
Close an ATS channel and release its resources.
No parameter schema on file.
Make a previously-started channel the active one for subsequent actions.
No parameter schema on file.
Mouse-click on an element on the active channel.
No parameter schema on file.
Type text into an element on the active channel.
No parameter schema on file.
Navigate the active web channel to a URL.
No parameter schema on file.
Navigate back in the browser history on the active web channel.
No parameter schema on file.
Navigate forward in the browser history on the active web channel.
No parameter schema on file.
Reload the current page on the active web channel.
No parameter schema on file.
Scroll the active channel by a pixel amount in a given direction.
No parameter schema on file.
Capture a screenshot of the active channel. Returns the file path of the PNG.
No parameter schema on file.
Dump the DOM (web) or view hierarchy (mobile/desktop) of the active channel.
No parameter schema on file.
Find elements matching a CSS selector (web) or a SAP tag (SAP channel). Returns indexed enumeration. Use capture_tree first to discover the structure.
No parameter schema on file.
Get JS console logs (log/warn/error) captured on the active web channel since it was opened.
No parameter schema on file.
List HTTP requests captured on the active web channel (URL, status, timing). Each request gets an index usable in network_detail.
No parameter schema on file.
Full request/response detail (headers, body) for one HTTP exchange — pass the index returned by network_list.
No parameter schema on file.
List cookies set on the active web channel.
No parameter schema on file.
Move the mouse over an element on the active channel.
No parameter schema on file.
Press and hold on an element (start of a drag — pair with drop).
No parameter schema on file.
Release on an element (end of a drag — must follow drag).
No parameter schema on file.
Select a <select> option by visible text, by value, or by 0-based index.
No parameter schema on file.
Press a special key (ENTER, TAB, ESC, arrows, F-keys…) — optionally on a target element.
No parameter schema on file.
Upload a local file to a file-input element.
No parameter schema on file.
Run JavaScript in the active web channel and return its value. ATS implicit waits do not apply — script runs once.
No parameter schema on file.
Resize (and optionally move) the active channel
No parameter schema on file.
Switch to another window/tab by index, name, or URL substring.
No parameter schema on file.
Open a new browser tab, optionally navigating to a URL.
No parameter schema on file.
Close the current window/tab on the active channel.
No parameter schema on file.
Handle a JS alert/confirm/prompt dialog: accept, dismiss, or click the default button. Pass
No parameter schema on file.
Run a sequence of raw ATS action lines (advanced: when a purpose-built tool above doesn
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- 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 Ats 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 81 / 100
Release 0.4.0 · 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 score88
Client score81
Findings5 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest99180c0c63ee3c254664513e377add1ab9f28369d28249a9ca59da82027b158a
Score vectorthreat 88 → client 81
| 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 surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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 |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
can execute shell commands or code
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 digest99180c0c63ee3c25
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 0.4.0. Pin a release below and the command asks for exactly that one.
0.4.0
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 Ats 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.