Local MCP capabilities provider for Expo
MobiLoop 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.
What it does
Guarded AI mobile Appium testing, security scanning, verification, and fix-retest MCP tools.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user mobiloop-mcp '--' docker run -i --rm ghcr.io/enessubass/mobiloop-mcp:0.1.0-alpha.15
# 2 — ask your agent for something these tools do
# flow.analyze_from_code, flow.generate_test_scenarios, flow.run_script and 79 more
MobiLoop costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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 MobiLoop 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. It has not been scanned here, so read the surface, and its source, before you approve it.
This is a public server: you run it yourself and this marketplace is not in the path. You need Docker installed and running. Only the required variables are passed into the container. To set an optional one (MOBILOOP_WORKSPACE_ROOT, APPIUM_SERVER_URL), add -e NAME before the image name and give it a value in the entry’s env: an unset -e would clear the default the image sets. 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 mobiloop-mcp '--' docker run -i --rm ghcr.io/enessubass/mobiloop-mcp:0.1.0-alpha.15Reconnect, or start a new session, and the tools appear in the model’s tool list.
Nothing is required, but it can take MOBILOOP_WORKSPACE_ROOT (Workspace path mounted into the container.), APPIUM_SERVER_URL (Appium server URL reachable from the container.) if you want to set them.
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.
82 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.
Infer mobile screens, routes, transitions, and visible text candidates from source code.
No parameter schema on file.
Generate candidate mobile E2E scenarios from static source-flow analysis for an AI agent to execute/refine.
No parameter schema on file.
Run a high-level JSON flow DSL over an Appium session: waitText, tapText, type, assertText, observe, collectEvidence, back, swipe, checkpoint.
No parameter schema on file.
Record a runtime screen checkpoint from Appium source/session and optional action needed to reach the next checkpoint.
No parameter schema on file.
Record the ordered checkpoint ids for a test run. The latest passed run becomes the default replay path.
No parameter schema on file.
Match the current screen against recorded checkpoints and return Appium actions needed to reach a target checkpoint.
No parameter schema on file.
Auto-advance an Appium session from a previously seen screen to the latest or requested checkpoint.
No parameter schema on file.
Read recorded flow checkpoints, runs, and code-flow analyses.
No parameter schema on file.
Clear flow memory under artifactsDir. This does not modify app source code.
No parameter schema on file.
Run build -> install -> Appium scripted test -> verification -> evidence -> loop record for Android.
No parameter schema on file.
Run iOS simulator build -> install/launch -> Appium XCUITest scripted test -> verification -> evidence -> loop record.
No parameter schema on file.
Create an Appium session. Pass W3C capabilities or raw capabilities object.
No parameter schema on file.
Delete an Appium session.
No parameter schema on file.
Capture screenshot and page source for the current Appium session, optionally waiting for app UI readiness.
No parameter schema on file.
Return raw Appium page source XML.
No parameter schema on file.
Return a compact accessibility summary parsed from page source.
No parameter schema on file.
Tap a visible element by text with exact-first matching before contains fallback.
No parameter schema on file.
Tap by accessibility id.
No parameter schema on file.
Tap by Android resource id or Appium id locator.
No parameter schema on file.
Tap screen coordinates. Use only when semantic locators are unavailable.
No parameter schema on file.
Type text into an element located by accessibility id, id, xpath, text, or native selector.
No parameter schema on file.
Perform a touch swipe by coordinates.
No parameter schema on file.
Send Android/iOS back navigation to the Appium session.
No parameter schema on file.
Wait until a locator becomes visible.
No parameter schema on file.
Assert that a locator is visible. Returns passed false instead of throwing when not visible.
No parameter schema on file.
Assert that a locator is not visible within timeout.
No parameter schema on file.
Detect Flutter, React Native, or native Android project type.
No parameter schema on file.
Install dependencies for the detected or specified mobile project type.
No parameter schema on file.
Run lint/static analysis for Flutter, React Native, or Android.
No parameter schema on file.
Run unit tests for Flutter, React Native, or Android.
No parameter schema on file.
Build a debug APK and return discovered APK artifact paths.
No parameter schema on file.
Build a release candidate APK. Release signing requirements are delegated to the target project.
No parameter schema on file.
List build log artifacts emitted by this MCP server.
No parameter schema on file.
Create a JSON manifest of files under the MCP artifacts directory.
No parameter schema on file.
Append Markdown to GitHub Actions step summary or a workspace fallback file.
No parameter schema on file.
Create a GitHub PR comment through gh. Uses current PR when prNumber is omitted.
No parameter schema on file.
Emit GitHub Actions warning/error annotations from findings.
No parameter schema on file.
Read a non-secret file inside workspaceRoot.
No parameter schema on file.
Search workspaceRoot. Uses ripgrep when available and falls back to a built-in scanner.
No parameter schema on file.
Apply a unified diff after validating all touched paths stay inside workspaceRoot and are not forbidden.
No parameter schema on file.
Return git diff for workspaceRoot.
No parameter schema on file.
Create and checkout a guarded feature branch. Branch must match allowedBranchPattern.
No parameter schema on file.
Commit changes only while on an allowed feature/ai branch. Optionally stage specific non-secret paths.
No parameter schema on file.
Open a pull request with GitHub CLI from the current allowed feature branch.
No parameter schema on file.
List Android devices via adb devices -l.
No parameter schema on file.
Start an Android emulator by AVD name. Returns after launching or optional boot wait.
No parameter schema on file.
Stop an Android emulator through adb emu kill.
No parameter schema on file.
Install or replace an APK on an Android device.
No parameter schema on file.
Uninstall an Android package from a device.
No parameter schema on file.
Clear app data for an Android package.
No parameter schema on file.
Grant one or more Android runtime permissions to a package.
No parameter schema on file.
Capture a PNG screenshot from an Android device into artifacts.
No parameter schema on file.
Pull Android logcat into artifacts. Optionally filter by package pid when available.
No parameter schema on file.
Check host/project readiness for Android, iOS, Flutter, React Native, CI, or all environments.
No parameter schema on file.
Return supported host/platform requirements for this MCP package.
No parameter schema on file.
Check Appium readiness, optionally install a driver and start a detached Appium server.
No parameter schema on file.
List available iOS simulators via xcrun simctl.
No parameter schema on file.
Boot an iOS simulator and optionally wait until boot completes.
No parameter schema on file.
Shutdown an iOS simulator.
No parameter schema on file.
Build an iOS simulator app with xcodebuild into MCP artifacts.
No parameter schema on file.
Install an .app bundle on an iOS simulator.
No parameter schema on file.
Launch an installed iOS simulator app by bundle id.
No parameter schema on file.
Capture an iOS simulator screenshot into artifacts.
No parameter schema on file.
Collect recent simulator logs into artifacts.
No parameter schema on file.
Append one build-test-verify loop iteration as JSONL evidence.
No parameter schema on file.
Generate a Markdown report from recorded iterations.
No parameter schema on file.
Read recorded loop iterations.
No parameter schema on file.
List effective tool policy metadata for MCP clients and approval gates.
No parameter schema on file.
Scan mobile source and platform configuration for deterministic security signals without running target code.
No parameter schema on file.
Generate a deterministic mobile security test plan from a source-scan report for an AI or engineer to execute.
No parameter schema on file.
Re-run the deterministic source scan and compare it with a baseline report after fixes.
No parameter schema on file.
Evaluate a source-scan report against a severity threshold before release or merge.
No parameter schema on file.
Assert current Appium page source contains expected text.
No parameter schema on file.
Assert logcat or a saved log file has no crash signatures.
No parameter schema on file.
Assert the Appium session and page source are reachable, distinguishing automation failures from app crashes.
No parameter schema on file.
Call an API and assert status and optional body substrings.
No parameter schema on file.
Collect screenshot, page source, and logcat evidence where available.
No parameter schema on file.
Assert a navigation target by expected Appium page source text.
No parameter schema on file.
Assert clickable or input-like nodes have a text, label, name, content-desc, or resource-id.
No parameter schema on file.
Compare two PNG screenshots and assert the pixel diff ratio is at or below maxDiffRatio.
No parameter schema on file.
Run a read-only sqlite query and assert exact output or expected substring.
No parameter schema on file.
Compute SHA-256 for a workspace artifact or evidence file.
No parameter schema on file.
- 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 MobiLoop or to call it, at any volume.
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.
This listing ships as a container image. The scanner reads packages on npm and PyPI and public source; an image is neither, so there is no grade here — not a withheld one, an unmeasured one.
Release history
It installs from a container image rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 0.1.0-alpha.14.
No release note was published with this version.
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.
Any signed-in account that does not publish MobiLoop can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.