# sniff (npm · sniff-qa)

Find broken pages in your running web app before users do. Each page bug comes with steps and a fix.

- Trust score: 79/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `sniff-qa`: 79/100 (this document), [markdown](https://verifymcp.io/servers/aboudjem-sniff/sniff-qa.md), [page](https://verifymcp.io/servers/aboudjem-sniff/sniff-qa)

## Channel facts

- Registry: `npm`
- Package: `sniff-qa`
- Version: `0.9.5`
- 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 2026-11-21.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 0 of 1 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to Aboudjem/sniff).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 3 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1079 tokens (~179/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - 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**: 90/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 69% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 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 sniff MCP server?

sniff runs locally as an npm package, launched with npx -y sniff-qa --mcp. 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 aboudjem-sniff -- npx -y sniff-qa --mcp
```

### Cursor

```json
{
  "mcpServers": {
    "aboudjem-sniff": {
      "command": "npx",
      "args": [
        "-y",
        "sniff-qa",
        "--mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "aboudjem-sniff": {
      "command": "npx",
      "args": [
        "-y",
        "sniff-qa",
        "--mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add aboudjem-sniff -- npx -y sniff-qa --mcp
```

### opencode

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

### Hermes

```yaml
mcp_servers:
  aboudjem-sniff:
    command: "npx"
    args: ["-y", "sniff-qa", "--mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "aboudjem-sniff": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "sniff-qa",
        "--mcp"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "aboudjem-sniff": {
      "command": "npx",
      "args": [
        "-y",
        "sniff-qa",
        "--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.

### 2026-11-18 (score 79, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-17 (score 64)

First indexed and scored.

## MCP tools (6)

### `sniff` (~398 tokens)

Find real, reproducible QA bugs in a web app. Pass { mode, rootDir, baseUrl? }. Use mode:"walk" (RECOMMENDED) to drive a real browser, walk the app's user flows, and report broken pages/links, console & network errors, empty/placeholder data, broken forms, state-loss, dead-ends, bad loading/error states, responsive issues and accessibility, each with reproduction proof, severity, confidence, and a fix. mode:"scan" = source-only (no browser). mode:"report" = load last results. (mode:"run"/"discover" are legacy.) Auto-detects a running dev server if baseUrl is omitted. Prefer this over the narrow tools (sniff_scan / sniff_run / sniff_discover / sniff_report).

Input parameters:

- `all` (boolean): walk: include low-confidence findings too (default false)
- `appType` (array)
- `baseUrl` (string): URL of the running app (walk/run/discover). Optional, auto-detected if omitted.
- `dryRun` (boolean)
- `forceAppType` (string)
- `format` (string)
- `headless` (boolean)
- `maxPages` (integer): walk: max pages to crawl (default 25)
- `maxScenarios` (integer)
- `maxVariantsPerRun` (integer)
- `maxVariantsPerScenario` (integer)
- `mobile` (boolean): walk: include the mobile (375px) responsive pass (default true)
- `mode` (string, required): walk = autonomous flow-walk that finds real bugs (RECOMMENDED for a running app); scan = source only; run/discover = legacy; report = load last results
- `only` (string)
- `realism` (string)
- `rootDir` (string, required): Absolute path to the project root directory
- `seed` (integer)

### `sniff_scan` (~78 tokens)

Scan project source code for bugs. Finds debug statements, placeholder text, dead links, broken imports, hardcoded URLs, and API endpoint issues (missing validation, auth, error handling, secrets). Works offline, no browser or API key needed. Just pass the project path.

Input parameters:

- `rootDir` (string, required): Absolute path to the project root directory

### `sniff_run` (~112 tokens)

Run a full quality audit: source scan + browser checks (accessibility, visual regression, performance). The URL is optional -- sniff auto-detects running dev servers. If no server is found, runs source scan only. No API key needed.

Input parameters:

- `baseUrl` (string): URL of the running app. Optional -- sniff auto-detects localhost servers if omitted.
- `headless` (boolean): Run browser in headless mode
- `rootDir` (string, required): Absolute path to the project root directory

### `sniff_discover` (~309 tokens)

Run autonomous end-to-end discovery: extract the app domain from source, classify the app type, generate scenarios with edge-case variants, drive them through Playwright, and return a compact summary. Requires a running dev server (baseUrl optional, auto-detected if omitted). Writes HTML/JSON reports to sniff-reports/discovery/.

Input parameters:

- `appType` (array): Filter classifier guesses to these app types (does NOT bypass classification; use forceAppType for that)
- `baseUrl` (string): URL of the running app. Optional -- sniff auto-detects localhost servers if omitted.
- `dryRun` (boolean): Generate scenarios + classify without launching a browser or writing reports. Useful for preview.
- `forceAppType` (string): Force a single app type, bypassing the classifier entirely. Use when classification returns blank.
- `headless` (boolean): Run browser in headless mode
- `maxScenarios` (integer): Cap total scenarios (default: 50)
- `maxVariantsPerRun` (integer): Cap edge variants per run (default: 40)
- `maxVariantsPerScenario` (integer): Cap edge variants per scenario (default: 3)
- `only` (string): Filter scenarios by id substring or app type
- `realism` (string): Realism profile (default: robot in CI, casual-user otherwise)
- `rootDir` (string, required): Absolute path to the project root directory
- `seed` (integer): Replay a specific random seed

### `sniff_install` (~124 tokens)

Download what a browser walk needs, once: the browser engine (Playwright, axe-core, Lighthouse) and the requested browsers (default: chromium). For chromium that is about 440 MB to download, about 730 MB on disk (measured on macOS arm64, varies by platform). Run this when a sniff tool returns `needsSetup: playwright-browsers`, then retry. It takes about a minute on a fast link; pass a progress token to get progress notifications.

Input parameters:

- `projects` (array): Browser projects to install. Defaults to ["chromium"].

### `sniff_report` (~58 tokens)

Get the results from the most recent sniff scan. Returns findings, severities, and fix suggestions.

Input parameters:

- `format` (string): Output format: full JSON or text summary
- `rootDir` (string, required): Absolute path to the project root directory

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/aboudjem-sniff/sniff-qa#diagnostics

## Score history

- 2026-11-21: 79
- 2026-11-20: 79
- 2026-11-19: 79
- 2026-11-18: 79
- 2026-11-17: 64

## Common questions

### What is the sniff MCP server?

sniff is an MCP server listed in the public MCP registry as io.github.Aboudjem/sniff. Find broken pages in your running web app before users do. Each page bug comes with steps and a fix. This page covers its npm package (sniff-qa).

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

sniff scores 79 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. 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 sniff MCP server expose?

sniff exposes 6 tools: sniff, sniff_scan, sniff_run, sniff_discover, sniff_install, sniff_report. Their descriptions and schemas cost roughly 1,079 tokens of context every time the server is loaded.

### Is the sniff MCP server still maintained?

sniff is still listed as active in the MCP registry. We last reached this channel on 21 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 sniff MCP server under?

sniff declares the Apache-2.0 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 sniff MCP server?

VerifyMCP ran 15 checks on sniff, covering Malware scan, Known CVEs, Install scripts, Dependency health and 11 more. One item could not be completed, a gap on our side rather than a finding about sniff: Stability. One category scores 0 for that reason, because we only credit what we can confirm. Endpoint Security and Transport & Reachability do not apply to an npm package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- npm package: https://www.npmjs.com/package/sniff-qa
- Socket report: https://socket.dev/npm/package/sniff-qa
- Repository: https://github.com/Aboudjem/sniff
- Changelog RSS feed: https://verifymcp.io/servers/aboudjem-sniff/sniff-qa.xml
- Changelog JSON feed: https://verifymcp.io/servers/aboudjem-sniff/sniff-qa/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/aboudjem-sniff/sniff-qa.json
- HTML version of this page: https://verifymcp.io/servers/aboudjem-sniff/sniff-qa
