# io.github.ZUHcYa/ai-validation (npm · ai-validation-mcp)

Independent AI code validation: test bias, edge cases, coverage gaps.

- Trust score: 62/100 (medium)
- Change this week: +22
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `ai-validation-mcp`: 62/100 (this document), [markdown](https://verifymcp.io/servers/zuhcya-ai-validation/ai-validation-mcp.md), [page](https://verifymcp.io/servers/zuhcya-ai-validation/ai-validation-mcp)

## Channel facts

- Registry: `npm`
- Package: `ai-validation-mcp`
- Version: `0.1.2`
- 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**: 88/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (121 of 122), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (121 of 122), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 133 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 229 tokens (~76/item across 3 items; 3 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.

## Install

### Claude

```bash
claude mcp add zuhcya-ai-validation -- npx -y ai-validation-mcp
```

### Codex

```bash
codex mcp add zuhcya-ai-validation -- npx -y ai-validation-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "zuhcya-ai-validation": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "ai-validation-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add zuhcya-ai-validation --command npx --arg -y --arg ai-validation-mcp
```

### Hermes

```yaml
mcp_servers:
  zuhcya-ai-validation:
    command: "npx"
    args: ["-y", "ai-validation-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "zuhcya-ai-validation": {
      "command": "npx",
      "args": [
        "-y",
        "ai-validation-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.

### 2026-08-03 (score 62, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-08-02 (score 58, +50)

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

### 2026-08-01 (score 8, −16)

- [functional regression] Tool coverage: 100 → unverified

### 2026-07-31 (score 24, +2)

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

### 2026-07-30 (score 22, +22)

- [security regression] Source repository: unverified → fail
- [functional improvement] Tool coverage: unverified → 100

### 2026-07-29 (score 0, −19)

- [security regression] Malware scan: pass → unverified
- [security regression] Provenance: fail → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-07-28 (score 19, −21)

- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Dependency health: unverified → partial
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 40)

First indexed and scored.

## MCP tools (3)

### `validate_tests` (~80 tokens)

Analyze existing tests for bias, missing edge cases, and quality issues. Returns bias warnings, missing edge case suggestions, and an overall quality score.

Input parameters:

- `language` (string): Programming language (default: typescript)
- `sourceCode` (string, required): The source code to validate tests against
- `testCode` (string, required): The existing test code to analyze

### `suggest_edge_cases` (~68 tokens)

Suggest comprehensive edge cases for a given function/code. Returns categorized edge cases: happy path, error handling, boundary, type coercion, integration.

Input parameters:

- `language` (string): Programming language (default: typescript)
- `sourceCode` (string, required): The source code to analyze for edge cases

### `coverage_gap_analysis` (~81 tokens)

Identify untested code paths, branches, and logic gaps in existing tests. Returns coverage score, gap details, and suggested tests to close gaps.

Input parameters:

- `language` (string): Programming language (default: typescript)
- `sourceCode` (string, required): The source code to analyze coverage for
- `testCode` (string, required): The existing test code to evaluate

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/zuhcya-ai-validation/ai-validation-mcp#diagnostics

## Score history

- 2026-08-03: 62
- 2026-08-02: 58
- 2026-08-01: 8
- 2026-07-31: 24
- 2026-07-30: 22
- 2026-07-29: 0
- 2026-07-28: 19
- 2026-07-27: 40

## Links

- npm package: https://www.npmjs.com/package/ai-validation-mcp
- Socket report: https://socket.dev/npm/package/ai-validation-mcp
- Changelog RSS feed: https://verifymcp.io/servers/zuhcya-ai-validation/ai-validation-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/zuhcya-ai-validation/ai-validation-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/zuhcya-ai-validation/ai-validation-mcp