# ghost-qa (npm · ghost-qa)

Autonomous headless browser QA & self-healing verification loop for AI coding agents.

- Trust score: 75/100 (medium)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- npm · `ghost-qa`: 75/100 (this document), [markdown](https://verifymcp.io/servers/avivgerz-hue-ghost-qa/ghost-qa.md), [page](https://verifymcp.io/servers/avivgerz-hue-ghost-qa/ghost-qa)

## Channel facts

- Registry: `npm`
- Package: `ghost-qa`
- Version: `2.1.2`
- 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 2026-11-21.

- **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 2 dependencies flagged as unhealthy.
- **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 3 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 546 tokens (~182/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 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.

## Install

### How do I install the ghost-qa MCP server?

ghost-qa runs locally as an npm package, launched with npx -y ghost-qa mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add avivgerz-hue-ghost-qa -- npx -y ghost-qa mcp
```

### Cursor

```json
{
  "mcpServers": {
    "avivgerz-hue-ghost-qa": {
      "command": "npx",
      "args": [
        "-y",
        "ghost-qa",
        "mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "avivgerz-hue-ghost-qa": {
      "command": "npx",
      "args": [
        "-y",
        "ghost-qa",
        "mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add avivgerz-hue-ghost-qa -- npx -y ghost-qa mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add avivgerz-hue-ghost-qa --command npx --arg -y --arg ghost-qa --arg mcp
```

### Hermes

```yaml
mcp_servers:
  avivgerz-hue-ghost-qa:
    command: "npx"
    args: ["-y", "ghost-qa", "mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "avivgerz-hue-ghost-qa": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "ghost-qa",
        "mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add avivgerz-hue-ghost-qa -t stdio -c npx -a -y ghost-qa mcp
```

### Other

```json
{
  "mcpServers": {
    "avivgerz-hue-ghost-qa": {
      "command": "npx",
      "args": [
        "-y",
        "ghost-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.

### 2026-11-20 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 74, +16)

- [security improvement] Malware scan: unverified → pass

### 2026-11-17 (score 58, −12)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Stability: unverified → 0.23
- [functional] Package version: 2.1.1 → 2.1.2

### 2026-11-11 (score 70, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-10 (score 55)

First indexed and scored.

## MCP tools (3)

### `ghost_qa_audit_url` (~246 tokens)

Run the full ghost-qa Deep Browser Inspection against a running localhost app: crawls internal routes on Desktop 1440x900, Tablet 768x1024 and Mobile 375x812 under light + dark colour schemes, safely exercises interactive controls, and runs the 8-Trap Engine (console/framework runtime, network/asset integrity, layout/geometry/collision, WCAG accessibility + keyboard focus, Core Web Vitals performance, link integrity, SEO/metadata, theme parity). Returns the Self-Healing Bug Report plus the QA Health Score (0-100, grade A+ to F) — fix every critical/major issue and re-audit until the score is 95+ before declaring the task done. Save the returned report JSON as before.json for ghost_qa_compare.

Input parameters:

- `maxDepth` (number): Link-following depth (default 2)
- `maxRoutes` (number): Maximum routes to visit (default 25)
- `url` (string, required): Target URL of the running app, e.g. http://localhost:3000
- `viewport` (string): Viewports to test (default all: desktop + tablet + mobile)

### `ghost_qa_compare` (~147 tokens)

Compare two ghost-qa JSON reports (the objects returned by ghost_qa_audit_url, or report.json files written by the CLI) and return the Regression & Verification Delta Report: scoreDelta, fixedFindings, newRegressions and remainingFindings. Use it after fixing bugs to prove the fix worked without introducing regressions; verified=true only at score >= 95 with zero regressions and no blocking findings left.

Input parameters:

- `after` (object, required): New ghost-qa report JSON (after fixes), e.g. the saved after.json object
- `before` (object, required): Baseline ghost-qa report JSON (before fixes), e.g. the saved before.json object

### `ghost_qa_doctor` (~45 tokens)

Verify ghost-qa environment readiness: Node.js version, Chromium binary availability, and a live headless-browser smoke test. Run this first when an audit fails to start.

## Diagnostics

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

## Score history

- 2026-11-21: 75
- 2026-11-20: 75
- 2026-11-19: 74
- 2026-11-18: 74
- 2026-11-17: 58
- 2026-11-16: 70
- 2026-11-15: 70
- 2026-11-14: 70
- 2026-11-13: 70
- 2026-11-12: 70
- 2026-11-11: 70
- 2026-11-10: 55

## Common questions

### What is the ghost-qa MCP server?

ghost-qa is an MCP server listed in the public MCP registry as io.github.avivgerz-hue/ghost-qa. Autonomous headless browser QA & self-healing verification loop for AI coding agents. This page covers its npm package (ghost-qa).

### Is the ghost-qa MCP server safe to use?

ghost-qa scores 75 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. 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 ghost-qa MCP server expose?

ghost-qa exposes 3 tools: ghost_qa_audit_url, ghost_qa_compare, ghost_qa_doctor. Their descriptions and schemas cost roughly 438 tokens of context every time the server is loaded.

### Is the ghost-qa MCP server still maintained?

ghost-qa 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 ghost-qa MCP server under?

ghost-qa 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 ghost-qa MCP server?

VerifyMCP ran 16 checks on ghost-qa, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. 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/ghost-qa
- Socket report: https://socket.dev/npm/package/ghost-qa
- Repository: https://github.com/avivgerz-hue/ghost-qa
- Changelog RSS feed: https://verifymcp.io/servers/avivgerz-hue-ghost-qa/ghost-qa.xml
- Changelog JSON feed: https://verifymcp.io/servers/avivgerz-hue-ghost-qa/ghost-qa/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/avivgerz-hue-ghost-qa/ghost-qa.json
- HTML version of this page: https://verifymcp.io/servers/avivgerz-hue-ghost-qa/ghost-qa
