# RankFabrik (npm · rankfabrik-mcp)

Proxy MCP des 4 API RankFabrik : Places, Jobs, Captions, Verify. Une cle federee pour les 4.

- Trust score: 71/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- npm · `rankfabrik-mcp`: 71/100 (this document), [markdown](https://verifymcp.io/servers/finalburner-rankfabrik-mcp/rankfabrik-mcp.md), [page](https://verifymcp.io/servers/finalburner-rankfabrik-mcp/rankfabrik-mcp)

## Channel facts

- Registry: `npm`
- Package: `rankfabrik-mcp`
- Version: `2.0.0`
- 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 2026-09-20.

- **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.
  - 31 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 (ISC).
  - Actively maintained (last published 4 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 81/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 1519 tokens (~116/item across 13 items; 13 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 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 RankFabrik MCP server?

RankFabrik runs locally as an npm package, launched with npx -y rankfabrik-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 finalburner-rankfabrik-mcp -- npx -y rankfabrik-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "finalburner-rankfabrik-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "rankfabrik-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "finalburner-rankfabrik-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "rankfabrik-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add finalburner-rankfabrik-mcp -- npx -y rankfabrik-mcp
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add finalburner-rankfabrik-mcp --command npx --arg -y --arg rankfabrik-mcp
```

### Hermes

```yaml
mcp_servers:
  finalburner-rankfabrik-mcp:
    command: "npx"
    args: ["-y", "rankfabrik-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "finalburner-rankfabrik-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "rankfabrik-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add finalburner-rankfabrik-mcp -t stdio -c npx -a -y rankfabrik-mcp
```

### Other

```json
{
  "mcpServers": {
    "finalburner-rankfabrik-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "rankfabrik-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.

### 2026-09-16 (score 71, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-15 (score 56)

First indexed and scored.

## MCP tools (13)

### `youtube_inspect` (~102 tokens)

Inspect a YouTube video

Return a YouTube video's metadata and the list of available subtitle tracks WITHOUT downloading the transcript. Free, no billing. Use this first to check a video has captions (and in which languages) before calling youtube_transcribe. Accepts a full YouTube URL (any format) or a bare 11-character video id.

Input parameters:

- `video` (string, required): YouTube video URL (watch, youtu.be, embed, shorts, live) or 11-char id

### `youtube_transcribe` (~221 tokens)

Transcribe a YouTube video

Get the full transcript of a YouTube video: complete text, timestamped segments, and optionally chapter-by-chapter text, SRT/VTT subtitle files, and salient verbatims with deep-links. Works on auto-generated captions (the majority of videos). Accepts a URL or bare id. Set segments=false for a lighter response. This is the billable product (1 unit when text is returned).

Input parameters:

- `chapitres` (boolean): Include chapter-by-chapter text and deep-links. Default false.
- `formats` (string): Subtitle export formats, comma-separated: 'srt', 'vtt', or 'srt,vtt'.
- `langues` (string): Preferred language order, comma-separated, e.g. 'fr,en'. Default 'fr,en'.
- `segments` (boolean): Include timestamped segments. Default true.
- `verbatims` (integer): Number of salient verbatim passages to extract (each with a ?t= deep-link).
- `video` (string, required): YouTube video URL or 11-char id

### `youtube_search` (~88 tokens)

Search YouTube videos

Search YouTube by a term and return matching video ids. Use this when you don't have a video id yet — feed the results into youtube_transcribe, or use youtube_harvest to search and transcribe in one call. Billed per returned id.

Input parameters:

- `combien` (integer): How many video ids to return. Default 20.
- `terme` (string, required): Search term / query

### `youtube_harvest` (~133 tokens)

Harvest transcripts by topic

Search YouTube for a topic and transcribe the matching videos in one call — the fast path for a themed corpus. Returns per-video transcripts plus completeness stats (how many carried human vs auto captions). Up to 30 videos. Billed per video actually transcribed.

Input parameters:

- `chapitres` (boolean): Include chapters per video. Default false.
- `combien` (integer): How many videos to harvest (max 30). Default 10.
- `langues` (string): Preferred language order, e.g. 'fr,en'. Default 'fr,en'.
- `terme` (string, required): Topic / search term

### `youtube_transcribe_batch` (~140 tokens)

Transcribe many YouTube videos

Transcribe up to 50 YouTube videos in parallel from a list of ids or URLs. Returns per-video transcripts plus completeness stats. Use when you already have the ids; use youtube_harvest when you only have a topic. Billed per video actually transcribed.

Input parameters:

- `chapitres` (boolean): Include chapters per video. Default false.
- `langues` (string): Preferred language order, e.g. 'fr,en'. Default 'fr,en'.
- `segments` (boolean): Include timestamped segments per video. Default false.
- `videos` (array, required): List of YouTube URLs or 11-char ids (max 50)

### `places_search` (~214 tokens)

Search local businesses (Places)

Find local businesses / points of interest matching a term around a location. Location is given EITHER by a known city name OR by latitude+longitude (provide one or the other). Optionally enrich with public contact e-mails, opening hours / distribution and photos. Returns up to 20 places. Billed per returned place.

Input parameters:

- `combien` (integer): How many places to return (max 20).
- `distribution` (boolean): Include opening hours / distribution data. Default false.
- `emails` (boolean): Enrich each place with public contact e-mails. Default false.
- `latitude` (number): Latitude (with longitude, as an alternative to ville)
- `longitude` (number): Longitude (with latitude, as an alternative to ville)
- `photos` (boolean): Include photos. Default false.
- `terme` (string, required): What to look for, e.g. 'plombier', 'coffee shop', 'notaire'
- `ville` (string): Known city name (use this OR latitude+longitude)

### `places_scan` (~158 tokens)

Scan an area for local businesses (Places)

Sweep a wider area for businesses matching a term by walking a grid of points around a location (city OR latitude+longitude). Deeper coverage than places_search. Billed per returned place.

Input parameters:

- `latitude` (number): Latitude (with longitude)
- `longitude` (number): Longitude (with latitude)
- `pages` (integer): Depth per point, 1-20. Default 1.
- `pas` (integer): Grid step, 2-6. Default 3.
- `rayonKm` (number): Grid radius in km. Default 4.
- `terme` (string, required): What to look for, e.g. 'restaurant', 'garage'
- `ville` (string): Known city name (use this OR latitude+longitude)

### `places_cities` (~53 tokens)

List known cities (Places)

List the city names Places recognises for the `ville` parameter of places_search / places_scan. Free, no billing. Use this to pick a valid city, or fall back to latitude+longitude for anywhere else.

### `jobs_search` (~106 tokens)

Search job offers (Jobs)

Search job offers by trade / role, optionally filtered by place. Returns matching offers (title, company, location, link). Billed per returned offer.

Input parameters:

- `combien` (integer): How many offers to return.
- `lieu` (string): Place filter, e.g. a city or region. Default: all of France.
- `metier` (string, required): Trade / role to search, e.g. 'développeur', 'infirmier', 'chef de projet'

### `jobs_full` (~104 tokens)

Search job offers with full detail (Jobs)

Search job offers and return the full detail of each (complete description and, optionally, the hiring company's profile). Heavier than jobs_search. Billed per returned offer.

Input parameters:

- `avecSociete` (boolean): Also resolve the hiring company's profile. Default false.
- `combien` (integer): How many offers to return. Default 20.
- `lieu` (string): Place filter. Default: all of France.
- `metier` (string, required): Trade / role to search

### `jobs_company` (~45 tokens)

Get a company's hiring profile (Jobs)

Resolve a single company's public hiring profile by name or slug. Billed per returned company.

Input parameters:

- `societe` (string, required): Company name or slug, e.g. 'Decathlon'

### `verify_email` (~86 tokens)

Verify one e-mail address (Verify)

Check whether a single e-mail address is deliverable: syntax, domain, MX records, and (by default) an SMTP probe. Returns a verdict and the signals behind it. Billed 1 unit per address.

Input parameters:

- `email` (string, required): The e-mail address to verify
- `sonder` (boolean): Perform the SMTP probe. Default true; set false for a lighter check.

### `verify_emails` (~69 tokens)

Verify many e-mail addresses (Verify)

Verify a list of e-mail addresses at once (syntax, domain, MX, SMTP probe). Returns a verdict per address. Billed per address actually checked.

Input parameters:

- `emails` (array, required): List of e-mail addresses to verify
- `sonder` (boolean): Perform the SMTP probe. Default true.

## Diagnostics

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

## Score history

- 2026-09-20: 71
- 2026-09-19: 71
- 2026-09-18: 71
- 2026-09-17: 71
- 2026-09-16: 71
- 2026-09-15: 56

## Common questions

### What is the RankFabrik MCP server?

RankFabrik is an MCP server listed in the public MCP registry as io.github.finalburner/rankfabrik-mcp. Proxy MCP des 4 API RankFabrik : Places, Jobs, Captions, Verify. Une cle federee pour les 4. This page covers its npm package (rankfabrik-mcp).

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

RankFabrik scores 71 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 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 RankFabrik MCP server expose?

RankFabrik exposes 13 tools: youtube_inspect, youtube_transcribe, youtube_search, youtube_harvest, youtube_transcribe_batch, and 8 more. Their descriptions and schemas cost roughly 1,519 tokens of context every time the server is loaded.

### Is the RankFabrik MCP server still maintained?

RankFabrik is still listed as active in the MCP registry. We last reached this channel on 20 September 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 RankFabrik MCP server under?

RankFabrik declares the ISC licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

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