# Frenchie (remote · mcp.getfrenchie.dev)

OCR, transcription, file extraction, and image generation for AI agents via MCP.

- Trust score: 71/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `mcp.getfrenchie.dev`: 71/100 (this document), [markdown](https://verifymcp.io/servers/lab94-frenchie-skill/mcp.md), [page](https://verifymcp.io/servers/lab94-frenchie-skill/mcp)
- npm · `@lab94/frenchie`: 32/100, [markdown](https://verifymcp.io/servers/lab94-frenchie-skill/lab94-frenchie.md), [page](https://verifymcp.io/servers/lab94-frenchie-skill/lab94-frenchie)

## Channel facts

- Endpoint: `https://mcp.getfrenchie.dev`
- Transports: `streamable-http`
- Auth: `required`
- Version: `0.5.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1066 tokens (~152/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http lab94-frenchie-skill https://mcp.getfrenchie.dev/
```

### Codex

```toml
[mcp_servers.lab94-frenchie-skill]
url = "https://mcp.getfrenchie.dev/"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "lab94-frenchie-skill": {
      "type": "remote",
      "url": "https://mcp.getfrenchie.dev/",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add lab94-frenchie-skill --url https://mcp.getfrenchie.dev/ --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  lab94-frenchie-skill:
    url: "https://mcp.getfrenchie.dev/"
```

### Other

```json
{
  "mcpServers": {
    "lab94-frenchie-skill": {
      "type": "http",
      "url": "https://mcp.getfrenchie.dev/"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-08-02 (score 71, +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.

### 2026-07-31 (score 70, +3)

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

### 2026-07-30 (score 67, 0)

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

### 2026-07-29 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-28 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 65, 0)

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

### 2026-07-26 (score 65)

First indexed and scored.

## MCP tools (7)

### `ocr_to_markdown` (~114 tokens)

OCR to Markdown

Convert PDF/image files into Markdown through Frenchie

Input parameters:

- `api_key` (string): Optional Frenchie API key (fr_...). Falls back to the FRENCHIE_API_KEY env var when omitted.
- `file_path` (string): Absolute local file path. Stdio transport only — over HTTP, upload via upload_file first and pass uploaded_file_reference instead.
- `uploaded_file_reference` (string): Object key returned by upload_file. Required for HTTP transport; ignored when file_path is provided in stdio.

Output parameters:

- `creditsUsed` (number)
- `estimatedCompletion` (string)
- `jobId` (string)
- `result`
- `resultExpiresAt` (string)
- `status` (string)

### `transcribe_to_markdown` (~184 tokens)

Transcribe to Markdown

Convert audio/video files into Markdown transcripts through Frenchie. Set language (ISO 639-1 code, e.g. 'th', 'en', 'ja') for better accuracy; omit for auto-detection.

Input parameters:

- `api_key` (string): Optional Frenchie API key (fr_...). Falls back to the FRENCHIE_API_KEY env var when omitted.
- `file_path` (string): Absolute local file path. Stdio transport only — over HTTP, upload via upload_file first and pass uploaded_file_reference instead.
- `language` (string): Optional ISO 639-1 language code (e.g. 'th', 'en', 'ja') for better accuracy; omit for auto-detection.
- `uploaded_file_reference` (string): Object key returned by upload_file. Required for HTTP transport; ignored when file_path is provided in stdio.

Output parameters:

- `creditsUsed` (number)
- `estimatedCompletion` (string)
- `jobId` (string)
- `result`
- `resultExpiresAt` (string)
- `status` (string)

### `generate_image` (~282 tokens)

Generate Image

Generate a single image from a text prompt through Frenchie. Required: prompt. Optional: style (free-text style direction), size, quality, format, background. stdio mode auto-saves the image to .frenchie/<slug>/generated.<ext>; HTTP mode returns a presigned imageUrl that the agent should download for the user.

Input parameters:

- `api_key` (string): Optional Frenchie API key (fr_...). Falls back to the FRENCHIE_API_KEY env var when omitted.
- `background` (string): Optional background. transparent is rejected when format is jpeg.
- `format` (string): Optional output format. Defaults to png.
- `output_dir` (string): Stdio mode only: absolute directory under which .frenchie/<slug>/generated.<ext> is saved. Defaults to the MCP server's process cwd. Recommended: pass your workspace root so the image lands next to y…
- `prompt` (string, required): Required. Plain-language description of the image to generate (e.g. 'poster of a ramen shop at night').
- `quality` (string): Optional output quality.
- `size` (string): Optional output size. Defaults to automatic selection.
- `style` (string): Optional style direction (e.g. 'flat vector, neon palette'). Merged into the generation prompt by Frenchie.

Output parameters:

- `creditsUsed` (number)
- `estimatedCompletion` (string)
- `jobId` (string)
- `result`
- `resultExpiresAt` (string)
- `status` (string)

### `extract_to_markdown` (~155 tokens)

Extract to Markdown

Extract structured documents (.docx, .xlsx, .csv, .tsv, .pptx) into Markdown through Frenchie. stdio mode auto-saves the result to .frenchie/<name>/result.md; HTTP mode returns inline Markdown.

Input parameters:

- `api_key` (string): Optional Frenchie API key (fr_...). Falls back to the FRENCHIE_API_KEY env var when omitted.
- `file_path` (string): Absolute local file path. Stdio transport only — over HTTP, upload via upload_file first and pass uploaded_file_reference instead.
- `uploaded_file_reference` (string): Object key returned by upload_file. Required for HTTP transport; ignored when file_path is provided in stdio.

Output parameters:

- `creditsUsed` (number)
- `estimatedCompletion` (string)
- `jobId` (string)
- `result`
- `resultExpiresAt` (string)
- `status` (string)

### `get_job_result` (~81 tokens)

Get Job Result

Fetch the latest async Frenchie job result

Input parameters:

- `api_key` (string): Optional Frenchie API key (fr_...). Falls back to the FRENCHIE_API_KEY env var when omitted.
- `job_id` (string, required): Job ID returned by ocr_to_markdown, transcribe_to_markdown, or generate_image when status was 'processing'.

Output parameters:

- `creditsUsed` (number)
- `estimatedCompletion` (string)
- `jobId` (string)
- `result`
- `resultExpiresAt` (string)
- `status` (string)

### `upload_file` (~153 tokens)

Upload File (HTTP)

Get a presigned upload URL for use with ocr_to_markdown, transcribe_to_markdown, or extract_to_markdown in HTTP mode. After calling this tool, PUT the file to upload_url (with the correct Content-Type header), then pass object_key as uploaded_file_reference to the processing tool.

Input parameters:

- `api_key` (string): Optional Frenchie API key (fr_...). Falls back to the FRENCHIE_API_KEY env var when omitted.
- `file_size` (integer, required): File size in bytes.
- `filename` (string, required): Original filename with extension (e.g. 'report.pdf').
- `mime_type` (string, required): MIME type (e.g. 'application/pdf', 'audio/mpeg').

Output parameters:

- `expires_in` (integer): URL expiry in seconds
- `object_key` (string): Pass this as uploaded_file_reference to ocr_to_markdown, transcribe_to_markdown, or extract_to_markdown
- `upload_url` (string): Presigned URL — PUT the file here with the correct Content-Type header

### `fetch_result_file` (~97 tokens)

Fetch Result File (HTTP)

Get a temporary download URL for a result file from OCR/transcription output. Use this to download images referenced as frenchie-result: in the result markdown.

Input parameters:

- `api_key` (string): Optional Frenchie API key (fr_...). Falls back to the FRENCHIE_API_KEY env var when omitted.
- `object_key` (string, required): The object key parsed from a frenchie-result:<objectKey> reference in the result markdown.

Output parameters:

- `download_url` (string): Temporary HTTPS download URL for the result file.
- `expires_in` (integer): URL expiry in seconds (typically 900).
- `filename` (string): Suggested filename derived from the original object key.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/lab94-frenchie-skill/mcp#diagnostics

## Score history

- 2026-08-03: 71
- 2026-08-02: 71
- 2026-08-01: 70
- 2026-07-31: 70
- 2026-07-30: 67
- 2026-07-29: 67
- 2026-07-28: 66
- 2026-07-27: 65
- 2026-07-26: 65

## Links

- Remote endpoint: https://mcp.getfrenchie.dev/
- Authorisation metadata: https://mcp.getfrenchie.dev/.well-known/oauth-protected-resource
- Repository: https://github.com/Lab94/frenchie-skill
- Website: https://getfrenchie.dev/
- Changelog RSS feed: https://verifymcp.io/servers/lab94-frenchie-skill/mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/lab94-frenchie-skill/mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/lab94-frenchie-skill/mcp