# Google CrUX MCP (npm · mcp-google-crux)

Real-user Core Web Vitals from the Chrome UX Report (CrUX) API for any origin or URL.

- Trust score: 66/100 (medium)
- Change this week: +28
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-20

## Components

- npm · `mcp-google-crux`: 66/100 (this document), [markdown](https://verifymcp.io/servers/a1-x-tech-mcp-google-crux/mcp-google-crux.md), [page](https://verifymcp.io/servers/a1-x-tech-mcp-google-crux/mcp-google-crux)

## Channel facts

- Registry: `npm`
- Package: `mcp-google-crux`
- Version: `1.1.0`
- 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 2026-08-20.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 30 of 96 dependencies flagged as unhealthy.
- **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 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 63/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 2385 tokens (~397/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**: 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 a1-x-tech-mcp-google-crux -- npx -y mcp-google-crux
```

### Codex

```bash
codex mcp add a1-x-tech-mcp-google-crux -- npx -y mcp-google-crux
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "a1-x-tech-mcp-google-crux": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "mcp-google-crux"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add a1-x-tech-mcp-google-crux --command npx --arg -y --arg mcp-google-crux
```

### Hermes

```yaml
mcp_servers:
  a1-x-tech-mcp-google-crux:
    command: "npx"
    args: ["-y", "mcp-google-crux"]
```

### Other

```json
{
  "mcpServers": {
    "a1-x-tech-mcp-google-crux": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-google-crux"
      ]
    }
  }
}
```

## 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.

### 2026-08-20 (score 66, 0)

- [functional] Package version: 1.0.0 → 1.1.0

### 2026-08-19 (score 66, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-08-18 (score 51, +13)

- [security regression] Malware scan: pass → unverified
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: excellent
- [functional] First check of Schema quality: fail
- [functional] First check of Tool coverage: 100
- [functional] Package version: 1.0.0 → 1.1.0

### 2026-08-13 (score 38, 0)

- [functional regression] Security disclosure: unverified → fail

### 2026-08-12 (score 38, 0)

- [functional regression] Security disclosure: fail → unverified

### 2026-08-11 (score 38, 0)

- [functional] Package version: 0.1.0 → 1.0.0
- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-08-09 (score 38)

First indexed and scored.

## MCP tools (6)

### `get_core_web_vitals` (~345 tokens)

Core Web Vitals assessment

One-call Core Web Vitals assessment for an origin or URL over the latest 28-day window. Per metric (LCP, INP, CLS + diagnostic FCP and TTFB): p75, rating (good | needs-improvement | poor, web.dev thresholds: LCP ≤2500ms/>4000ms, INP ≤200ms/>500ms, CLS ≤0.10/>0.25) and the good/needs_improvement/poor user-experience densities (~sum 1.0). `passes_core_web_vitals` is true when all three CWV rate good. Timings are ms; CLS is unitless. Returns {no_data: true} when the origin/URL has insufficient traffic in CrUX. Provide exactly one of `origin` or `url`.

Input parameters:

- `form_factor` (string): Device class filter. Omit for the aggregated record across all devices. tablet traffic is tiny and usually has no data.
- `origin` (string): Site origin — scheme + host only, e.g. https://example.com (no path, no trailing slash). Aggregates real-user data across ALL pages of the site. Mutually exclusive with `url`. http/https and www/non-…
- `url` (string): A specific page URL, e.g. https://example.com/pricing/. Mutually exclusive with `origin`. Pass the final post-redirect URL (the API does not follow redirects); fragments and query params are stripped…

### `compare_form_factors` (~312 tokens)

Phone vs desktop vs tablet

Compares real-user performance across device classes for an origin or URL: one aggregated all-devices record plus phone, desktop and tablet records (4 API requests = 4 quota units of the 150/min budget). Per device: p75 + rating per metric; `traffic_share` gives each device's fraction of page loads (from the unfiltered form_factors metric). Devices without enough data come back as {no_data: true} — expected for tablet almost always. Default metrics: the three Core Web Vitals. Provide exactly one of `origin` or `url`.

Input parameters:

- `metrics` (array): Metric names to return; omit for all available metrics. Timings are integer milliseconds; cumulative_layout_shift is a string-encoded double. form_factors is only returned when form_factor is NOT set.
- `origin` (string): Site origin — scheme + host only, e.g. https://example.com (no path, no trailing slash). Aggregates real-user data across ALL pages of the site. Mutually exclusive with `url`. http/https and www/non-…
- `url` (string): A specific page URL, e.g. https://example.com/pricing/. Mutually exclusive with `origin`. Pass the final post-redirect URL (the API does not follow redirects); fragments and query params are stripped…

### `compare_origin_vs_url` (~238 tokens)

Origin vs specific page

Compares the site-wide origin record against one specific page (2 API requests): p75 + rating per metric for each, so you can tell whether a page is faster or slower than the site average. Either side can come back {no_data: true} (single pages often lack data; redirecting homepages can lack origin data while pages have it). Default metrics: the three Core Web Vitals. Both `origin` AND `url` are required here (unlike the other tools).

Input parameters:

- `form_factor` (string): Device class filter. Omit for the aggregated record across all devices. tablet traffic is tiny and usually has no data.
- `metrics` (array): Metric names to return; omit for all available metrics. Timings are integer milliseconds; cumulative_layout_shift is a string-encoded double. form_factors is only returned when form_factor is NOT set.
- `origin` (string, required): Site origin — scheme + host only, e.g. https://example.com. Required.
- `url` (string, required): The page URL to compare against the origin, e.g. https://example.com/pricing/. Required.

### `get_cwv_trend` (~388 tokens)

Core Web Vitals trend

Weekly p75 trend for an origin or URL from the CrUX History API (1 request). Per metric: `points` — array of {period_end, p75, rating}, one per week (each week is a 28-day rolling window ending on period_end; ineligible weeks are skipped), and `delta` — first vs last p75 with direction improved | regressed | stable (lower is always better). Default metrics: the three Core Web Vitals; `weeks` caps the history depth (1..40, default 25). History data updates on Mondays. Returns {no_data: true} when CrUX has no data. Provide exactly one of `origin` or `url`.

Input parameters:

- `form_factor` (string): Device class filter. Omit for the aggregated record across all devices. tablet traffic is tiny and usually has no data.
- `metrics` (array): Metrics to trend (only p75-bearing metrics); default: the three Core Web Vitals (largest_contentful_paint, interaction_to_next_paint, cumulative_layout_shift).
- `origin` (string): Site origin — scheme + host only, e.g. https://example.com (no path, no trailing slash). Aggregates real-user data across ALL pages of the site. Mutually exclusive with `url`. http/https and www/non-…
- `url` (string): A specific page URL, e.g. https://example.com/pricing/. Mutually exclusive with `origin`. Pass the final post-redirect URL (the API does not follow redirects); fragments and query params are stripped…
- `weeks` (integer): How many weekly periods of history to analyze (1..40; default 25).

### `query_record` (~387 tokens)

Latest CrUX record (raw)

Returns the latest 28-day rolling CrUX record for an origin or URL (raw API response, updated daily ~04:00 UTC). Per metric: `histogram` (3 bins good/needs-improvement/poor with `density`), `percentiles.p75`, and for enum metrics `fractions`. Timings are integer ms; cumulative_layout_shift p75 is a string-encoded double (e.g. "0.05"). `collectionPeriod` always spans 28 days. `urlNormalizationDetails` appears if the URL was normalized (e.g. fragment stripped). A no-data answer (HTTP 404) is returned as {no_data: true} — not an error. Prefer get_core_web_vitals for a ready-made assessment; use this for full histograms/fractions.

Input parameters:

- `form_factor` (string): Device class filter. Omit for the aggregated record across all devices. tablet traffic is tiny and usually has no data.
- `metrics` (array): Metric names to return; omit for all available metrics. Timings are integer milliseconds; cumulative_layout_shift is a string-encoded double. form_factors is only returned when form_factor is NOT set.
- `origin` (string): Site origin — scheme + host only, e.g. https://example.com (no path, no trailing slash). Aggregates real-user data across ALL pages of the site. Mutually exclusive with `url`. http/https and www/non-…
- `url` (string): A specific page URL, e.g. https://example.com/pricing/. Mutually exclusive with `origin`. Pass the final post-redirect URL (the API does not follow redirects); fragments and query params are stripped…

### `query_history_record` (~386 tokens)

CrUX weekly timeseries (raw)

Returns the weekly CrUX timeseries for an origin or URL (raw API response, updated Mondays ~04:00 UTC): up to 40 collection periods, each a 28-day rolling window. Per metric: `histogramTimeseries` (bins with `densities` arrays), `percentilesTimeseries.p75s` and `fractionTimeseries`; all series align with `record.collectionPeriods`. Ineligible periods appear as null p75s and "NaN" densities — tolerate non-numeric entries. A no-data answer (HTTP 404) is returned as {no_data: true}. Prefer get_cwv_trend for a cleaned p75 trend.

Input parameters:

- `collection_period_count` (integer): How many weekly collection periods to return (1..40; API default 25).
- `form_factor` (string): Device class filter. Omit for the aggregated record across all devices. tablet traffic is tiny and usually has no data.
- `metrics` (array): Metric names to return; omit for all available metrics. Timings are integer milliseconds; cumulative_layout_shift is a string-encoded double. form_factors is only returned when form_factor is NOT set.
- `origin` (string): Site origin — scheme + host only, e.g. https://example.com (no path, no trailing slash). Aggregates real-user data across ALL pages of the site. Mutually exclusive with `url`. http/https and www/non-…
- `url` (string): A specific page URL, e.g. https://example.com/pricing/. Mutually exclusive with `origin`. Pass the final post-redirect URL (the API does not follow redirects); fragments and query params are stripped…

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/a1-x-tech-mcp-google-crux/mcp-google-crux#diagnostics

## Score history

- 2026-08-20: 66
- 2026-08-19: 66
- 2026-08-18: 51
- 2026-08-17: 38
- 2026-08-16: 38
- 2026-08-15: 38
- 2026-08-14: 38
- 2026-08-13: 38
- 2026-08-12: 38
- 2026-08-11: 38
- 2026-08-10: 38
- 2026-08-09: 38

## Links

- npm package: https://www.npmjs.com/package/mcp-google-crux
- Socket report: https://socket.dev/npm/package/mcp-google-crux
- Repository: https://github.com/A1-x-Tech/mcp-google-crux
- Changelog RSS feed: https://verifymcp.io/servers/a1-x-tech-mcp-google-crux/mcp-google-crux.xml
- Changelog JSON feed: https://verifymcp.io/servers/a1-x-tech-mcp-google-crux/mcp-google-crux.json
- HTML version of this page: https://verifymcp.io/servers/a1-x-tech-mcp-google-crux/mcp-google-crux