# io.github.MUSE-CODE-SPACE/test-genie (npm · test-genie-mcp)

AI-powered app test automation for iOS, Android, Flutter, React Native, Web

- Trust score: 58/100 (low)
- Change this week: +12
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `test-genie-mcp`: 58/100 (this document), [markdown](https://verifymcp.io/servers/muse-code-space-test-genie/test-genie-mcp.md), [page](https://verifymcp.io/servers/muse-code-space-test-genie/test-genie-mcp)

## Channel facts

- Registry: `npm`
- Package: `test-genie-mcp`
- Version: `2.0.3`
- 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 2026-08-03.

- **Supply Chain Security**: 70/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects uuid 9.0.1, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (150 of 154), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - 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 27 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1317 tokens (~69/item across 19 items; 19 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **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

### Claude

```bash
claude mcp add muse-code-space-test-genie -- npx -y test-genie-mcp
```

### Codex

```bash
codex mcp add muse-code-space-test-genie -- npx -y test-genie-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "muse-code-space-test-genie": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "test-genie-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add muse-code-space-test-genie --command npx --arg -y --arg test-genie-mcp
```

### Hermes

```yaml
mcp_servers:
  muse-code-space-test-genie:
    command: "npx"
    args: ["-y", "test-genie-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "muse-code-space-test-genie": {
      "command": "npx",
      "args": [
        "-y",
        "test-genie-mcp"
      ]
    }
  }
}
```

## 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.

### 2026-08-02 (score 58, +37)

- [security regression] CVE-2026-41907 affects this package: high
- [security regression] Known CVEs: unverified → fail
- [security regression] Provenance: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Security disclosure: fail → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-08-01 (score 21, +16)

- [functional improvement] Tool coverage: unverified → 100

### 2026-07-31 (score 5, −23)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 28, −18)

- [security regression] Malware scan: pass → unverified

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (19)

### `analyze_app_structure` (~80 tokens)

Analyze app codebase structure including screens, components, APIs, and state management. Supports iOS, Android, Flutter, React Native, and Web platforms.

Input parameters:

- `depth` (string): Analysis depth level
- `platform` (string): Target platform (auto-detected if not provided)
- `projectPath` (string, required): Path to the project root directory

### `generate_scenarios` (~97 tokens)

Generate test scenarios based on app structure analysis. Creates E2E, integration, unit, performance, and memory test scenarios.

Input parameters:

- `coverage` (string): Coverage level
- `focusAreas` (array): Specific areas to focus on
- `maxScenarios` (number): Maximum number of scenarios to generate
- `projectPath` (string, required): Path to the project
- `testTypes` (array): Types of tests to generate

### `create_test_plan` (~92 tokens)

Create a test plan from generated scenarios with filtering and scheduling options.

Input parameters:

- `maxDuration` (number): Maximum duration in seconds
- `name` (string, required): Name of the test plan
- `priorityFilter` (array): Filter by priority
- `projectPath` (string, required): Path to the project
- `template` (string): Use a predefined template
- `typeFilter` (array): Filter by test type

### `run_scenario_test` (~87 tokens)

Run a specific test scenario and get detailed results.

Input parameters:

- `device` (string): Target device or simulator
- `platform` (string, required): Target platform
- `projectPath` (string, required): Path to the project
- `retries` (number): Number of retry attempts
- `scenarioId` (string, required): ID of the scenario to run
- `timeout` (number): Timeout in milliseconds

### `run_simulation` (~79 tokens)

Run user behavior simulation to find issues through random/pattern-based testing.

Input parameters:

- `duration` (number, required): Simulation duration in seconds
- `intensity` (string): Interaction intensity
- `monitorMetrics` (array): Metrics to monitor
- `projectPath` (string, required): Path to the project
- `userPatterns` (array): User behavior patterns to simulate

### `run_stress_test` (~92 tokens)

Run stress/load tests on APIs or UI components.

Input parameters:

- `concurrency` (number, required): Number of concurrent users/requests
- `duration` (number, required): Test duration in seconds
- `endpoints` (array): Specific endpoints to test
- `projectPath` (string, required): Path to the project
- `rampUp` (number): Ramp up time in seconds
- `targetType` (string, required): What to stress test

### `detect_memory_leaks` (~67 tokens)

Detect memory leaks, retain cycles, and unclosed resources through static and dynamic analysis.

Input parameters:

- `analysisType` (string): Type of analysis
- `minLeakSizeMB` (number): Minimum leak size to report (MB)
- `projectPath` (string, required): Path to the project

### `detect_logic_errors` (~63 tokens)

Detect logic errors including race conditions, state inconsistencies, null references, and type mismatches.

Input parameters:

- `analysisDepth` (string): Analysis depth
- `checkTypes` (array): Types of errors to check
- `projectPath` (string, required): Path to the project

### `suggest_fixes` (~55 tokens)

Generate AI-powered fix suggestions for detected issues.

Input parameters:

- `issueIds` (array): Specific issue IDs to fix
- `maxSuggestions` (number): Maximum suggestions to generate
- `projectPath` (string, required): Path to the project

### `confirm_fix` (~68 tokens)

Confirm or reject a suggested fix before application.

Input parameters:

- `action` (string, required): Confirmation action
- `fixId` (string, required): ID of the fix to confirm
- `modifiedCode` (string): Modified code if action is modify
- `reason` (string): Reason for rejection if action is reject

### `apply_fix` (~65 tokens)

Apply a confirmed fix to the codebase.

Input parameters:

- `backup` (boolean): Create backup before applying
- `dryRun` (boolean): Preview changes without applying
- `fixId` (string, required): ID of the fix to apply
- `validate` (boolean): Validate syntax after applying

### `rollback_fix` (~32 tokens)

Rollback an applied fix to restore original code.

Input parameters:

- `fixId` (string, required): ID of the fix to rollback

### `run_full_automation` (~93 tokens)

Run complete test automation pipeline: analyze → generate scenarios → run tests → detect issues → suggest fixes. Interactive confirmation for fixes.

Input parameters:

- `autoFix` (boolean): Automatically apply high-confidence fixes
- `confirmMode` (string): Fix confirmation mode
- `platform` (string): Target platform
- `projectPath` (string, required): Path to the project
- `testTypes` (array): Types of tests to run

### `generate_report` (~66 tokens)

Generate detailed test automation report in Markdown, HTML, or JSON format.

Input parameters:

- `format` (string): Report format
- `outputPath` (string): Path to save the report
- `projectPath` (string, required): Path to the project
- `sections` (array): Sections to include

### `get_pending_fixes` (~32 tokens)

Get list of pending fix suggestions waiting for confirmation.

Input parameters:

- `projectPath` (string, required): Path to the project

### `get_test_history` (~40 tokens)

Get test execution history for a project.

Input parameters:

- `limit` (number): Maximum results to return
- `projectPath` (string, required): Path to the project

### `analyze_performance` (~49 tokens)

Deep performance analysis including rendering, computation, network, and bundle size issues. Provides actionable recommendations.

Input parameters:

- `platform` (string): Target platform
- `projectPath` (string, required): Path to the project

### `analyze_code_deep` (~50 tokens)

Deep AST-based code analysis with function extraction, complexity metrics, hook analysis, and issue detection.

Input parameters:

- `platform` (string): Target platform
- `projectPath` (string, required): Path to the project

### `generate_cicd_config` (~110 tokens)

Generate CI/CD configuration for GitHub Actions, Jenkins, or GitLab CI with test automation integration.

Input parameters:

- `branches` (array): Branches to run CI on
- `buildCommand` (string): Custom build command
- `platform` (string): Target platform
- `projectPath` (string, required): Path to the project
- `provider` (string, required): CI/CD provider
- `testCommand` (string): Custom test command
- `writeToFile` (boolean): Write config to project

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/muse-code-space-test-genie/test-genie-mcp#diagnostics

## Score history

- 2026-08-03: 58
- 2026-08-02: 58
- 2026-08-01: 21
- 2026-07-31: 5
- 2026-07-30: 28
- 2026-07-28: 46
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/test-genie-mcp
- Socket report: https://socket.dev/npm/package/test-genie-mcp
- Repository: https://github.com/MUSE-CODE-SPACE/test-genie-mcp
- Changelog RSS feed: https://verifymcp.io/servers/muse-code-space-test-genie/test-genie-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/muse-code-space-test-genie/test-genie-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/muse-code-space-test-genie/test-genie-mcp