# Fleets (npm · fleets-mcp)

Multi-site analytics as tools: GA4, Search Console, Cloudflare edge, PageSpeed, insights.

- Trust score: 69/100 (medium)
- Change this week: +23
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `fleets-mcp`: 69/100 (this document), [markdown](https://verifymcp.io/servers/runfleets-cli/fleets-mcp.md), [page](https://verifymcp.io/servers/runfleets-cli/fleets-mcp)

## Channel facts

- Registry: `npm`
- Package: `fleets-mcp`
- Version: `0.2.2`
- 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**: 86/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 102), 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 (95 of 102), so this covers what we could see, not the whole tree.
- **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 29 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 1183 tokens (~65/item across 18 items; 18 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 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 runfleets-cli -- npx -y fleets-mcp
```

### Codex

```bash
codex mcp add runfleets-cli -- npx -y fleets-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add runfleets-cli --command npx --arg -y --arg fleets-mcp
```

### Hermes

```yaml
mcp_servers:
  runfleets-cli:
    command: "npx"
    args: ["-y", "fleets-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "runfleets-cli": {
      "command": "npx",
      "args": [
        "-y",
        "fleets-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 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 68, +30)

- [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] Maintenance: pass → unverified
- [functional regression] License: pass → unverified
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] MCP protocol: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 38, −5)

- [security] Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet.
- [functional regression] Capabilities: pass → unverified

### 2026-07-31 (score 43, −7)

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

### 2026-07-30 (score 50, −30)

- [security regression] Known CVEs: partial → unverified
- [security regression] Malware scan: pass → unverified
- [functional regression] Dependency health: partial → unverified

### 2026-07-29 (score 80, +54)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [functional regression] Security disclosure: unverified → fail
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] License: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → excellent
- [functional] Licence: MIT

### 2026-07-28 (score 26, −20)

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

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (18)

### `list_sites` (~40 tokens)

List all sites on your Fleets account with their connected sources (GA4 property, Cloudflare zone, GSC site). Start here to get slugs.

### `stats` (~68 tokens)

GA4 summary for a site: sessions, users, pageviews, events, engagement, bounce.

Input parameters:

- `range` (string): time range e.g. 7d, 30d, 24h (default 7d)
- `slug` (string, required): site slug (from list_sites)

### `sources` (~74 tokens)

GA4 top traffic sources / channels for a site.

Input parameters:

- `limit` (string): max rows to return (default: all)
- `range` (string): time range e.g. 7d, 30d, 24h (default 7d)
- `slug` (string, required): site slug (from list_sites)

### `campaigns` (~73 tokens)

GA4 UTM campaign breakdown for a site.

Input parameters:

- `limit` (string): max rows to return (default: all)
- `range` (string): time range e.g. 7d, 30d, 24h (default 7d)
- `slug` (string, required): site slug (from list_sites)

### `referrals` (~72 tokens)

GA4 referral traffic breakdown for a site.

Input parameters:

- `limit` (string): max rows to return (default: all)
- `range` (string): time range e.g. 7d, 30d, 24h (default 7d)
- `slug` (string, required): site slug (from list_sites)

### `landers` (~73 tokens)

GA4 top landing pages for a site.

Input parameters:

- `limit` (string): max rows to return (default: all)
- `range` (string): time range e.g. 7d, 30d, 24h (default 7d)
- `slug` (string, required): site slug (from list_sites)

### `events` (~79 tokens)

GA4 event breakdown (event name, count, users) for a site.

Input parameters:

- `limit` (string): max rows to return (default: all)
- `range` (string): time range e.g. 7d, 30d, 24h (default 7d)
- `slug` (string, required): site slug (from list_sites)

### `users` (~63 tokens)

GA4 user + session breakdown (country + device) for a site.

Input parameters:

- `range` (string): time range e.g. 7d, 30d, 24h (default 7d)
- `slug` (string, required): site slug (from list_sites)

### `devices` (~59 tokens)

GA4 device-category breakdown with engagement and bounce rate.

Input parameters:

- `range` (string): time range e.g. 7d, 30d, 24h (default 7d)
- `slug` (string, required): site slug (from list_sites)

### `demographics` (~59 tokens)

GA4 age + gender breakdown (requires Google Signals).

Input parameters:

- `range` (string): time range e.g. 7d, 30d, 24h (default 7d)
- `slug` (string, required): site slug (from list_sites)

### `funnel` (~77 tokens)

GA4 conversion funnel across two or more event/step names.

Input parameters:

- `range` (string): time range e.g. 7d, 30d, 24h (default 7d)
- `slug` (string, required): site slug (from list_sites)
- `steps` (array, required): two or more funnel step names, in order

### `seo` (~66 tokens)

Google Search Console summary (clicks, impressions, CTR, position) for a site.

Input parameters:

- `range` (string): time range e.g. 7d, 30d, 24h (default 7d)
- `slug` (string, required): site slug (from list_sites)

### `edge` (~66 tokens)

Cloudflare edge analytics for a site: bots vs humans, cache hit rate, requests.

Input parameters:

- `range` (string): time range e.g. 7d, 30d, 24h (default 7d)
- `slug` (string, required): site slug (from list_sites)

### `speed` (~47 tokens)

PageSpeed Insights score + Core Web Vitals for a site's homepage.

Input parameters:

- `slug` (string, required): site slug (from list_sites)
- `strategy` (string): mobile (default) or desktop

### `insights` (~44 tokens)

AI-ready signals worth investigating across all sites, or filtered to one. Each insight includes a ready-to-run prompt.

Input parameters:

- `site` (string): optional: filter to one site slug

### `ask` (~55 tokens)

Ask a natural-language analytics question; the Fleets agent runs the right tools server-side and returns an answer with citations.

Input parameters:

- `model` (string): model (default haiku)
- `question` (string, required): the question, plain English

### `log_change` (~106 tokens)

Record a change you or your agent made to a site (deploy, copy edit, campaign) so it can be correlated with analytics later.

Input parameters:

- `actor` (string): optional actor label (default: agent)
- `description` (string, required): what changed, plain English
- `path` (string): optional page path e.g. /pricing
- `site` (string, required): site slug the change targets
- `tag` (string): optional tag e.g. campaign, content, fix

### `recall` (~62 tokens)

Show recent logged changes for a site (from log_change / `fleets log`).

Input parameters:

- `since` (string): time range e.g. 7d, 30d (default 30d)
- `slug` (string, required): site slug (from list_sites)

## Diagnostics

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

## Score history

- 2026-08-03: 69
- 2026-08-02: 68
- 2026-08-01: 38
- 2026-07-31: 43
- 2026-07-30: 50
- 2026-07-29: 80
- 2026-07-28: 26
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/fleets-mcp
- Socket report: https://socket.dev/npm/package/fleets-mcp
- Repository: https://github.com/runFleets/cli
- Website: https://fleets.run/
- Changelog RSS feed: https://verifymcp.io/servers/runfleets-cli/fleets-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/runfleets-cli/fleets-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/runfleets-cli/fleets-mcp