Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

ghost-qa

NPM · GHOST-QA

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

Available components

+5 this week 75 Trust /100

Last scanned (19 hours ago)

Scores higher than 51% of npm servers

Category Testing and QA

Trust breakdown (7 categories)

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. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 0 of 2 dependencies flagged as unhealthy. View diagnostics → Pass
Provenance & Transparency48
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 3 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability69
  • AI-judged instruction clarity (good).Pass
  • 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. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management37
  • Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Nov 26 +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.

  • 18 Nov 26 +16
    • Malware scan: unverified → pass ▲ security
  • 17 Nov 26 −12
    • Malware scan: pass → unverified ▼ security
    • Stability: unverified → 0.23 ▲ functional
    • Package version: 2.1.1 → 2.1.2 functional
  • 11 Nov 26 +15
    • Malware scan: unverified → pass ▲ security
  • 10 Nov 26 55

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed npm/ghost-qa@2.1.2

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 2 packages
Packages resolved 2
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 3 exposed · ~438 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
ghost_qa_audit_url ~246

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.

NameTypeReqDescription
maxDepthnumber–Link-following depth (default 2)
maxRoutesnumber–Maximum routes to visit (default 25)
urlstringyesTarget URL of the running app, e.g. http://localhost:3000
viewportstring–Viewports to test (default all: desktop + tablet + mobile)

No output schema declared.

No examples provided.

ghost_qa_compare ~147

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.

NameTypeReqDescription
afterobjectyesNew ghost-qa report JSON (after fixes), e.g. the saved after.json object
beforeobjectyesBaseline ghost-qa report JSON (before fixes), e.g. the saved before.json object

No output schema declared.

No examples provided.

ghost_qa_doctor ~45

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

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.

npm · ghost-qa

# add to Claude Code
claude mcp add avivgerz-hue-ghost-qa -- npx -y ghost-qa mcp
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.