# MobiLoop (oci · ghcr.io/enessubass/mobiloop-mcp)

Guarded AI mobile Appium testing, security scanning, verification, and fix-retest MCP tools.

- Trust score: 46/100 (low)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- oci · `ghcr.io/enessubass/mobiloop-mcp`: 46/100 (this document), [markdown](https://verifymcp.io/servers/enessubass-mobiloop-mcp/ghcr-io-enessubass-mobiloop-mcp.md), [page](https://verifymcp.io/servers/enessubass-mobiloop-mcp/ghcr-io-enessubass-mobiloop-mcp)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/enessubass/mobiloop-mcp`
- Version: `0.1.0-alpha.15`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM or dependency manifest, so there is no dependency list to read.
- **Provenance & Transparency**: 48/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 20 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 68/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 4907 tokens (~59/item across 83 items; 83 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 70/100
  - Stability observed for 21 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 67/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "device.uninstall_app" implies "uninstall" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 83 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the MobiLoop MCP server?

MobiLoop runs locally as a container image, launched with docker run --rm -i -e MOBILOOP_WORKSPACE_ROOT -e APPIUM_SERVER_URL ghcr.io/enessubass/mobiloop-mcp:0.1.0-alpha.15. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add enessubass-mobiloop-mcp -- docker run --rm -i -e MOBILOOP_WORKSPACE_ROOT -e APPIUM_SERVER_URL ghcr.io/enessubass/mobiloop-mcp:0.1.0-alpha.15
```

This image reads MOBILOOP_WORKSPACE_ROOT and APPIUM_SERVER_URL. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Cursor

```json
{
  "mcpServers": {
    "enessubass-mobiloop-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "MOBILOOP_WORKSPACE_ROOT",
        "-e",
        "APPIUM_SERVER_URL",
        "ghcr.io/enessubass/mobiloop-mcp:0.1.0-alpha.15"
      ]
    }
  }
}
```

This image reads MOBILOOP_WORKSPACE_ROOT and APPIUM_SERVER_URL. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### VS Code

```json
{
  "servers": {
    "enessubass-mobiloop-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "MOBILOOP_WORKSPACE_ROOT",
        "-e",
        "APPIUM_SERVER_URL",
        "ghcr.io/enessubass/mobiloop-mcp:0.1.0-alpha.15"
      ]
    }
  }
}
```

This image reads MOBILOOP_WORKSPACE_ROOT and APPIUM_SERVER_URL. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Codex

```bash
codex mcp add enessubass-mobiloop-mcp -- docker run --rm -i -e MOBILOOP_WORKSPACE_ROOT -e APPIUM_SERVER_URL ghcr.io/enessubass/mobiloop-mcp:0.1.0-alpha.15
```

This image reads MOBILOOP_WORKSPACE_ROOT and APPIUM_SERVER_URL. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "enessubass-mobiloop-mcp": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "-e",
        "MOBILOOP_WORKSPACE_ROOT",
        "-e",
        "APPIUM_SERVER_URL",
        "ghcr.io/enessubass/mobiloop-mcp:0.1.0-alpha.15"
      ],
      "enabled": true
    }
  }
}
```

This image reads MOBILOOP_WORKSPACE_ROOT and APPIUM_SERVER_URL. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Hermes

```yaml
mcp_servers:
  enessubass-mobiloop-mcp:
    command: "docker"
    args: ["run", "--rm", "-i", "-e", "MOBILOOP_WORKSPACE_ROOT", "-e", "APPIUM_SERVER_URL", "ghcr.io/enessubass/mobiloop-mcp:0.1.0-alpha.15"]
```

This image reads MOBILOOP_WORKSPACE_ROOT and APPIUM_SERVER_URL. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Netclaw

```json
{
  "McpServers": {
    "enessubass-mobiloop-mcp": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "-e",
        "MOBILOOP_WORKSPACE_ROOT",
        "-e",
        "APPIUM_SERVER_URL",
        "ghcr.io/enessubass/mobiloop-mcp:0.1.0-alpha.15"
      ]
    }
  }
}
```

This image reads MOBILOOP_WORKSPACE_ROOT and APPIUM_SERVER_URL. Set them in your client's env block for this server; docker run -e passes each one through to the container.

### Other

```json
{
  "mcpServers": {
    "enessubass-mobiloop-mcp": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "-e",
        "MOBILOOP_WORKSPACE_ROOT",
        "-e",
        "APPIUM_SERVER_URL",
        "ghcr.io/enessubass/mobiloop-mcp:0.1.0-alpha.15"
      ]
    }
  }
}
```

This image reads MOBILOOP_WORKSPACE_ROOT and APPIUM_SERVER_URL. Set them in your client's env block for this server; docker run -e passes each one through to the container.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 46, +1)

No change was recorded against any check on this day. Stability & Change Management went from 67 to 70. That category is still filling its 30-day observation window: 20 days of observed history at the previous scan, 21 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 45, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 44, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 43, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 42, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 41, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-24 (score 40, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-21 (score 39, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (83)

### `code.read_file` (~33 tokens)

Read a non-secret file inside workspaceRoot.

Input parameters:

- `maxBytes` (number)
- `path` (string, required)

### `code.search_code` (~49 tokens)

Search workspaceRoot. Uses ripgrep when available and falls back to a built-in scanner.

Input parameters:

- `glob` (string)
- `maxResults` (number)
- `query` (string, required)

### `code.apply_patch` (~46 tokens)

[approval required][workspace write][risk:dangerous] Apply a unified diff after validating all touched paths stay inside workspaceRoot and are not forbidden.

Input parameters:

- `patch` (string, required)

### `code.git_diff` (~23 tokens)

Return git diff for workspaceRoot.

Input parameters:

- `staged` (boolean)

### `code.create_branch` (~44 tokens)

[approval required][workspace write][risk:dangerous] Create and checkout a guarded feature branch. Branch must match allowedBranchPattern.

Input parameters:

- `branchName` (string, required)

### `code.commit_changes` (~55 tokens)

[approval required][workspace write][risk:dangerous] Commit changes only while on an allowed feature/ai branch. Optionally stage specific non-secret paths.

Input parameters:

- `message` (string, required)
- `paths` (array)

### `code.open_pr` (~64 tokens)

[approval required][workspace write][risk:dangerous] Open a pull request with GitHub CLI from the current allowed feature branch.

Input parameters:

- `base` (string)
- `body` (string, required)
- `draft` (boolean)
- `title` (string, required)

### `env.preflight` (~37 tokens)

Check host/project readiness for Android, iOS, Flutter, React Native, CI, or all environments.

Input parameters:

- `target` (string)

### `env.compatibility_matrix` (~20 tokens)

Return supported host/platform requirements for this MCP package.

### `env.ensure_appium` (~121 tokens)

[approval required][workspace write][network][risk:network] Check Appium readiness, optionally install a driver and start a detached Appium server.

Input parameters:

- `address` (string)
- `appiumCommand` (string)
- `appiumHome` (string)
- `driverName` (string)
- `installDriver` (boolean)
- `port` (number)
- `serverUrl` (string)
- `startServer` (boolean)
- `timeoutMs` (number)
- `useNpx` (boolean)

### `build.detect_project` (~21 tokens)

Detect Flutter, React Native, or native Android project type.

### `build.install_dependencies` (~41 tokens)

[approval required][workspace write][network][risk:dangerous] Install dependencies for the detected or specified mobile project type.

Input parameters:

- `kind` (string)

### `build.run_lint` (~44 tokens)

[approval required][workspace write][network][risk:dangerous] Run lint/static analysis for Flutter, React Native, or Android.

Input parameters:

- `kind` (string)

### `build.run_unit_tests` (~43 tokens)

[approval required][workspace write][network][risk:dangerous] Run unit tests for Flutter, React Native, or Android.

Input parameters:

- `kind` (string)

### `build.build_debug_apk` (~43 tokens)

[approval required][workspace write][network][risk:dangerous] Build a debug APK and return discovered APK artifact paths.

Input parameters:

- `kind` (string)

### `build.build_release_candidate` (~47 tokens)

[approval required][workspace write][network][risk:dangerous] Build a release candidate APK. Release signing requirements are delegated to the target project.

Input parameters:

- `kind` (string)

### `build.collect_build_logs` (~20 tokens)

List build log artifacts emitted by this MCP server.

### `device.list_devices` (~18 tokens)

List Android devices via adb devices -l.

### `device.start_emulator` (~65 tokens)

[approval required][device mutation][risk:dangerous] Start an Android emulator by AVD name. Returns after launching or optional boot wait.

Input parameters:

- `avdName` (string, required)
- `timeoutMs` (number)
- `waitForBoot` (boolean)

### `device.stop_emulator` (~39 tokens)

[approval required][device mutation][risk:dangerous] Stop an Android emulator through adb emu kill.

Input parameters:

- `serial` (string)

### `device.install_app` (~46 tokens)

[approval required][device mutation][risk:dangerous] Install or replace an APK on an Android device.

Input parameters:

- `apkPath` (string, required)
- `serial` (string)

### `device.uninstall_app` (~46 tokens)

[approval required][device mutation][risk:dangerous] Uninstall an Android package from a device.

Input parameters:

- `packageName` (string, required)
- `serial` (string)

### `device.clear_app_data` (~45 tokens)

[approval required][device mutation][risk:dangerous] Clear app data for an Android package.

Input parameters:

- `packageName` (string, required)
- `serial` (string)

### `device.grant_permissions` (~55 tokens)

[approval required][device mutation][risk:dangerous] Grant one or more Android runtime permissions to a package.

Input parameters:

- `packageName` (string, required)
- `permissions` (array, required)
- `serial` (string)

### `device.capture_screenshot` (~35 tokens)

Capture a PNG screenshot from an Android device into artifacts.

Input parameters:

- `prefix` (string)
- `serial` (string)

### `device.pull_logs` (~56 tokens)

Pull Android logcat into artifacts. Optionally filter by package pid when available.

Input parameters:

- `clearAfter` (boolean)
- `outputPath` (string)
- `packageName` (string)
- `serial` (string)

### `ios.list_simulators` (~23 tokens)

List available iOS simulators via xcrun simctl.

### `ios.boot_simulator` (~58 tokens)

[approval required][device mutation][risk:dangerous] Boot an iOS simulator and optionally wait until boot completes.

Input parameters:

- `device` (string, required)
- `timeoutMs` (number)
- `waitForBoot` (boolean)

### `ios.shutdown_simulator` (~35 tokens)

[approval required][device mutation][risk:dangerous] Shutdown an iOS simulator.

Input parameters:

- `device` (string, required)

### `ios.build_app` (~100 tokens)

[device mutation][risk:device] Build an iOS simulator app with xcodebuild into MCP artifacts.

Input parameters:

- `buildSettings` (object)
- `configuration` (string)
- `derivedDataPath` (string)
- `destination` (string)
- `project` (string)
- `scheme` (string, required)
- `sdk` (string)
- `workspace` (string)
- `xcodebuildArgs` (array)

### `ios.install_app` (~47 tokens)

[approval required][device mutation][risk:dangerous] Install an .app bundle on an iOS simulator.

Input parameters:

- `appPath` (string, required)
- `device` (string)

### `ios.launch_app` (~55 tokens)

[approval required][device mutation][risk:dangerous] Launch an installed iOS simulator app by bundle id.

Input parameters:

- `bundleId` (string, required)
- `device` (string)
- `terminateRunning` (boolean)

### `ios.capture_screenshot` (~33 tokens)

Capture an iOS simulator screenshot into artifacts.

Input parameters:

- `device` (string)
- `prefix` (string)

### `ios.collect_logs` (~44 tokens)

Collect recent simulator logs into artifacts.

Input parameters:

- `device` (string)
- `last` (string)
- `predicate` (string)
- `prefix` (string)

### `appium.create_session` (~53 tokens)

[approval required][device mutation][risk:dangerous] Create an Appium session. Pass W3C capabilities or raw capabilities object.

Input parameters:

- `capabilities` (object, required)
- `serverUrl` (string)

### `appium.delete_session` (~44 tokens)

[approval required][device mutation][risk:dangerous] Delete an Appium session.

Input parameters:

- `serverUrl` (string)
- `sessionId` (string, required)

### `appium.observe_screen` (~97 tokens)

Capture screenshot and page source for the current Appium session, optionally waiting for app UI readiness.

Input parameters:

- `minWaitMs` (number)
- `prefix` (string)
- `serverUrl` (string)
- `sessionId` (string, required)
- `stableMs` (number)
- `timeoutMs` (number)
- `waitForAnyText` (array)
- `waitForPackageIdle` (boolean)

### `appium.get_page_source` (~35 tokens)

Return raw Appium page source XML.

Input parameters:

- `serverUrl` (string)
- `sessionId` (string, required)

### `appium.get_accessibility_tree` (~38 tokens)

Return a compact accessibility summary parsed from page source.

Input parameters:

- `serverUrl` (string)
- `sessionId` (string, required)

### `appium.tap_by_text` (~76 tokens)

[approval required][device mutation][risk:dangerous] Tap a visible element by text with exact-first matching before contains fallback.

Input parameters:

- `matchMode` (string)
- `serverUrl` (string)
- `sessionId` (string, required)
- `text` (string, required)
- `timeoutMs` (number)

### `appium.tap_by_accessibility_id` (~54 tokens)

[approval required][device mutation][risk:dangerous] Tap by accessibility id.

Input parameters:

- `accessibilityId` (string, required)
- `serverUrl` (string)
- `sessionId` (string, required)

### `appium.tap_by_resource_id` (~59 tokens)

[approval required][device mutation][risk:dangerous] Tap by Android resource id or Appium id locator.

Input parameters:

- `resourceId` (string, required)
- `serverUrl` (string)
- `sessionId` (string, required)

### `appium.tap_coordinates` (~65 tokens)

[approval required][device mutation][risk:dangerous] Tap screen coordinates. Use only when semantic locators are unavailable.

Input parameters:

- `serverUrl` (string)
- `sessionId` (string, required)
- `x` (number, required)
- `y` (number, required)

### `appium.hide_keyboard` (~56 tokens)

[approval required][device mutation][risk:dangerous] Hide a visible software keyboard and verify it is hidden; never sends a generic back action.

Input parameters:

- `serverUrl` (string)
- `sessionId` (string, required)

### `appium.type_text` (~87 tokens)

[approval required][device mutation][risk:dangerous] Type text into an element located by accessibility id, id, xpath, text, or native selector.

Input parameters:

- `clearFirst` (boolean)
- `locator` (object, required)
- `mode` (string)
- `serverUrl` (string)
- `sessionId` (string, required)
- `text` (string, required)

### `appium.swipe` (~85 tokens)

[approval required][device mutation][risk:dangerous] Perform a touch swipe by coordinates.

Input parameters:

- `durationMs` (number)
- `endX` (number, required)
- `endY` (number, required)
- `serverUrl` (string)
- `sessionId` (string, required)
- `startX` (number, required)
- `startY` (number, required)

### `appium.go_back` (~50 tokens)

[approval required][device mutation][risk:dangerous] Send Android/iOS back navigation to the Appium session.

Input parameters:

- `serverUrl` (string)
- `sessionId` (string, required)

### `appium.wait_for_visible` (~49 tokens)

Wait until a locator becomes visible.

Input parameters:

- `locator` (object, required)
- `serverUrl` (string)
- `sessionId` (string, required)
- `timeoutMs` (number)

### `appium.assert_visible` (~58 tokens)

Assert that a locator is visible. Returns passed false instead of throwing when not visible.

Input parameters:

- `locator` (object, required)
- `serverUrl` (string)
- `sessionId` (string, required)
- `timeoutMs` (number)

### `appium.assert_not_visible` (~52 tokens)

Assert that a locator is not visible within timeout.

Input parameters:

- `locator` (object, required)
- `serverUrl` (string)
- `sessionId` (string, required)
- `timeoutMs` (number)

### `verify.assert_screen_contains_text` (~44 tokens)

Assert current Appium page source contains expected text.

Input parameters:

- `serverUrl` (string)
- `sessionId` (string, required)
- `text` (string, required)

### `verify.assert_no_crash_in_logcat` (~50 tokens)

Assert logcat or a saved log file has no crash signatures.

Input parameters:

- `logPath` (string)
- `packageName` (string)
- `serial` (string)

### `verify.assert_appium_session_healthy` (~47 tokens)

Assert the Appium session and page source are reachable, distinguishing automation failures from app crashes.

Input parameters:

- `serverUrl` (string)
- `sessionId` (string, required)

### `verify.assert_api_response` (~81 tokens)

[network][risk:network] Call an API and assert status and optional body substrings.

Input parameters:

- `body` (string)
- `bodyContains` (array)
- `expectedStatus` (number)
- `headers` (object)
- `method` (string)
- `timeoutMs` (number)
- `url` (string, required)

### `verify.collect_evidence` (~61 tokens)

Collect screenshot, page source, and logcat evidence where available.

Input parameters:

- `packageName` (string)
- `prefix` (string)
- `serial` (string)
- `serverUrl` (string)
- `sessionId` (string)

### `verify.assert_navigation_reached` (~56 tokens)

Assert a navigation target by expected Appium page source text.

Input parameters:

- `expectedText` (string, required)
- `serverUrl` (string)
- `sessionId` (string, required)
- `sourceEvidencePrefix` (string)

### `verify.assert_accessibility_labels` (~56 tokens)

Assert clickable or input-like nodes have a text, label, name, content-desc, or resource-id.

Input parameters:

- `serverUrl` (string)
- `sessionId` (string)
- `sourcePath` (string)

### `verify.assert_screenshot_diff` (~61 tokens)

Compare two PNG screenshots and assert the pixel diff ratio is at or below maxDiffRatio.

Input parameters:

- `actualPath` (string, required)
- `baselinePath` (string, required)
- `maxDiffRatio` (number)
- `threshold` (number)

### `verify.assert_sqlite_query` (~56 tokens)

Run a read-only sqlite query and assert exact output or expected substring.

Input parameters:

- `databasePath` (string, required)
- `expectedOutput` (string)
- `outputContains` (string)
- `query` (string, required)

### `verify.hash_artifact` (~29 tokens)

Compute SHA-256 for a workspace artifact or evidence file.

Input parameters:

- `path` (string, required)

### `flow.analyze_from_code` (~43 tokens)

Infer mobile screens, routes, transitions, and visible text candidates from source code.

Input parameters:

- `includeTests` (boolean)
- `maxFiles` (number)

### `flow.generate_test_scenarios` (~74 tokens)

Generate candidate mobile E2E scenarios from static source-flow analysis for an AI agent to execute/refine.

Input parameters:

- `goal` (string)
- `includeNegativeCases` (boolean)
- `includeTests` (boolean)
- `maxFiles` (number)
- `maxScenarios` (number)

### `flow.run_script` (~114 tokens)

[approval required][device mutation][risk:dangerous] Run a high-level JSON flow DSL over an Appium session: waitText, tapText, type, hideKeyboard, assertText, observe, collectEvidence, back, swipe, checkpoint.

Input parameters:

- `delayMs` (number)
- `prefix` (string)
- `serverUrl` (string)
- `sessionId` (string, required)
- `steps` (array, required)
- `stopOnFailure` (boolean)
- `testName` (string)

### `flow.record_checkpoint` (~122 tokens)

[workspace write][risk:write] Record a runtime screen checkpoint from Appium source/session and optional action needed to reach the next checkpoint.

Input parameters:

- `actionToNext` (object)
- `checkpointId` (string)
- `name` (string, required)
- `order` (number)
- `prefix` (string)
- `screenshotPath` (string)
- `serverUrl` (string)
- `sessionId` (string)
- `source` (string)
- `sourcePath` (string)
- `testName` (string, required)

### `flow.record_test_run` (~92 tokens)

[workspace write][risk:write] Record the ordered checkpoint ids for a test run. The latest passed run becomes the default replay path.

Input parameters:

- `artifacts` (array)
- `checkpointIds` (array, required)
- `finishedAt` (string)
- `runId` (string)
- `startedAt` (string)
- `status` (string, required)
- `testName` (string, required)

### `flow.plan_replay` (~85 tokens)

Match the current screen against recorded checkpoints and return Appium actions needed to reach a target checkpoint.

Input parameters:

- `minimumScore` (number)
- `serverUrl` (string)
- `sessionId` (string)
- `source` (string)
- `sourcePath` (string)
- `targetCheckpointId` (string)
- `testName` (string)

### `flow.replay_to_checkpoint` (~99 tokens)

[approval required][device mutation][risk:dangerous] Auto-advance an Appium session from a previously seen screen to the latest or requested checkpoint.

Input parameters:

- `delayMs` (number)
- `dryRun` (boolean)
- `minimumScore` (number)
- `serverUrl` (string)
- `sessionId` (string, required)
- `targetCheckpointId` (string)
- `testName` (string)

### `flow.read_memory` (~21 tokens)

Read recorded flow checkpoints, runs, and code-flow analyses.

### `flow.clear_memory` (~43 tokens)

[approval required][workspace write][risk:dangerous] Clear flow memory under artifactsDir. This does not modify app source code.

Input parameters:

- `confirm` (string, required)

### `loop.record_iteration` (~104 tokens)

[workspace write][risk:write] Append one build-test-verify loop iteration as JSONL evidence.

Input parameters:

- `artifacts` (array)
- `build` (string)
- `device` (string)
- `failure` (string)
- `fix` (string)
- `goal` (string, required)
- `iteration` (number, required)
- `retest` (string)
- `root_cause` (string)
- `test_result` (string, required)

### `loop.generate_report` (~47 tokens)

[workspace write][risk:write] Generate a Markdown report from recorded iterations.

Input parameters:

- `finalStatus` (string)
- `summary` (string)
- `title` (string)

### `loop.read_iterations` (~14 tokens)

Read recorded loop iterations.

### `ci.collect_artifact_manifest` (~23 tokens)

Create a JSON manifest of files under the MCP artifacts directory.

### `ci.write_github_step_summary` (~49 tokens)

[workspace write][risk:write] Append Markdown to GitHub Actions step summary or a workspace fallback file.

Input parameters:

- `markdown` (string)
- `sourcePath` (string)

### `ci.comment_pr` (~64 tokens)

[approval required][workspace write][network][risk:dangerous] Create a GitHub PR comment through gh. Uses current PR when prNumber is omitted.

Input parameters:

- `body` (string)
- `bodyPath` (string)
- `prNumber` (string)

### `ci.create_github_annotations` (~50 tokens)

[workspace write][risk:write] Emit GitHub Actions warning/error annotations from findings.

Input parameters:

- `findings` (array, required)
- `level` (string)
- `title` (string)

### `orchestrator.run_android_validation_loop` (~233 tokens)

[approval required][device mutation][risk:dangerous] Run build -> install -> Appium scripted test -> verification -> evidence -> loop record for Android.

Input parameters:

- `apiChecks` (array)
- `apkPath` (string)
- `appiumCapabilities` (object)
- `appiumSteps` (array)
- `avdName` (string)
- `buildDebugApk` (boolean)
- `clearAppData` (boolean)
- `collectEvidence` (boolean)
- `expectedTexts` (array)
- `flowReplayBeforeSteps` (boolean)
- `flowReplayMinimumScore` (number)
- `flowReplayTargetCheckpointId` (string)
- `flowReplayTestName` (string)
- `goal` (string, required)
- `installDependencies` (boolean)
- `iterationOffset` (number)
- `kind` (string)
- `maxTestIterations` (number)
- `packageName` (string)
- `runLint` (boolean)
- `runUnitTests` (boolean)
- `serial` (string)

### `orchestrator.run_ios_validation_loop` (~358 tokens)

[approval required][device mutation][risk:dangerous] Run iOS simulator build -> install/launch -> Appium XCUITest scripted test -> verification -> evidence -> loop record.

Input parameters:

- `appPath` (string)
- `appiumCapabilities` (object)
- `appiumSteps` (array)
- `bootSimulator` (boolean)
- `buildIosApp` (boolean)
- `buildSettings` (object)
- `bundleId` (string)
- `captureSimulatorScreenshot` (boolean)
- `collectEvidence` (boolean)
- `collectSimulatorLogs` (boolean)
- `configuration` (string)
- `derivedDataPath` (string)
- `destination` (string)
- `device` (string)
- `evidenceTimeoutMs` (number)
- `expectedTexts` (array)
- `flowReplayBeforeSteps` (boolean)
- `flowReplayMinimumScore` (number)
- `flowReplayTargetCheckpointId` (string)
- `flowReplayTestName` (string)
- `goal` (string, required)
- `installApp` (boolean)
- `installDependencies` (boolean)
- `iterationOffset` (number)
- `kind` (string)
- `launchApp` (boolean)
- `maxTestIterations` (number)
- `project` (string)
- `runLint` (boolean)
- `runUnitTests` (boolean)
- `scheme` (string)
- `sdk` (string)
- `simulatorDevice` (string)
- `simulatorLogLast` (string)
- `simulatorLogPredicate` (string)
- `workspace` (string)
- `xcodebuildArgs` (array)

### `security.scan_source` (~39 tokens)

Scan mobile source and platform configuration for deterministic security signals without running target code.

Input parameters:

- `maxFiles` (number)
- `paths` (array)

### `security.generate_test_plan` (~39 tokens)

Generate a deterministic mobile security test plan from a source-scan report for an AI or engineer to execute.

Input parameters:

- `reportPath` (string, required)

### `security.compare_scans` (~49 tokens)

Re-run the deterministic source scan and compare it with a baseline report after fixes.

Input parameters:

- `baselinePath` (string, required)
- `maxFiles` (number)
- `paths` (array)

### `security.release_gate` (~42 tokens)

Evaluate a source-scan report against a severity threshold before release or merge.

Input parameters:

- `failAtOrAbove` (string)
- `reportPath` (string, required)

### `policy.list_tools` (~53 tokens)

List effective tool policy metadata for MCP clients and approval gates.

Input parameters:

- `includeDescriptions` (boolean)
- `requiresApproval` (boolean)
- `riskLevel` (string)
- `toolName` (string)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/enessubass-mobiloop-mcp/ghcr-io-enessubass-mobiloop-mcp#diagnostics

## Score history

- 2026-11-05: 46
- 2026-11-04: 45
- 2026-11-03: 45
- 2026-11-02: 44
- 2026-11-01: 44
- 2026-10-31: 43
- 2026-10-30: 43
- 2026-10-29: 42
- 2026-10-28: 42
- 2026-10-27: 41
- 2026-10-26: 41
- 2026-10-25: 40
- 2026-10-24: 40
- 2026-10-23: 39
- 2026-10-22: 39
- 2026-10-21: 39
- 2026-10-20: 38
- 2026-10-19: 38
- 2026-10-18: 37
- 2026-10-17: 37
- 2026-10-16: 36
- 2026-10-15: 36

## Common questions

### What is the MobiLoop MCP server?

MobiLoop is an MCP server listed in the public MCP registry as io.github.enessubass/mobiloop-mcp. Guarded AI mobile Appium testing, security scanning, verification, and fix-retest MCP tools. This page covers its container image (ghcr.io/enessubass/mobiloop-mcp).

### Is the MobiLoop MCP server safe to use?

MobiLoop scores 46 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the MobiLoop MCP server expose?

MobiLoop exposes 83 tools: code.read_file, code.search_code, code.apply_patch, code.git_diff, code.create_branch, and 78 more. Their descriptions and schemas cost roughly 4,907 tokens of context every time the server is loaded.

### Is the MobiLoop MCP server still maintained?

MobiLoop is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the MobiLoop MCP server under?

MobiLoop declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the MobiLoop MCP server?

VerifyMCP ran 12 checks on MobiLoop, covering Source repository, Provenance, License, Maintenance and 8 more. 4 items could not be completed, a gap on our side rather than a finding about MobiLoop: Malware scan, Known CVEs, Install scripts and Dependency health. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to a container image, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- GitHub Container Registry: https://ghcr.io/enessubass/mobiloop-mcp
- Repository: https://github.com/enessubass/mobiloop-mcp
- Website: https://enessubass.github.io/mobiloop-mcp/
- Changelog RSS feed: https://verifymcp.io/servers/enessubass-mobiloop-mcp/ghcr-io-enessubass-mobiloop-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/enessubass-mobiloop-mcp/ghcr-io-enessubass-mobiloop-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/enessubass-mobiloop-mcp/ghcr-io-enessubass-mobiloop-mcp.json
- HTML version of this page: https://verifymcp.io/servers/enessubass-mobiloop-mcp/ghcr-io-enessubass-mobiloop-mcp