# Frenchie

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

- name: io.github.Lab94/frenchie-skill
- version: 0.5.0
- connection class: R1 (autonomous)
- trust: 90/100
- quality: 84/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.Lab94%2Ffrenchie-skill
- tools: https://api.protogrid.dev/v1/servers/io.github.Lab94%2Ffrenchie-skill/tools

**An agent can connect on its own if it already holds `FRENCHIE_SKILL_TOKEN`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "frenchie-skill": {
      "type": "http",
      "url": "https://mcp.getfrenchie.dev",
      "headers": {
        "Authorization": "Bearer ${FRENCHIE_SKILL_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${FRENCHIE_SKILL_TOKEN}`.

## Trust

- hygiene: 100
- liveness: 100
- freshness: 65
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-100% ~updated-166d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 84/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 7 of 7 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,809 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: no tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: 50 (weight 15)

- warn `deps.known_vulns`: 2 advisories of lower severity or without a published fix: GHSA-5v7r-6r5c-r473 in file-type@20.5.0 (direct, fixed in 21.3.1), GHSA-j47w-4g3g-c36v in file-type@20.5.0 (direct, fixed in 21.3.2)
- fail `deps.mcp_sdk_version`: @modelcontextprotocol/sdk 1.30.1 has 1 known advisory (GHSA-6qxp-vccf-f47h); update @modelcontextprotocol/sdk to 1.31.0 or later
- pass `deps.resolvable`: @lab94/frenchie@0.5.0 resolved: 135 packages

- tools: 7, about 1,809 tokens to load them all
- tool set hash: 1855b5aa5fbd76af1d55011954c9ceb4
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.Lab94/frenchie-skill.svg)](https://protogrid.dev/servers/io.github.Lab94/frenchie-skill)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

_No tool definition changes recorded._

## Dependencies

- npm @lab94/frenchie@0.5.0: resolved, 134 dependencies, MCP SDK @modelcontextprotocol/sdk 1.30.1
  - GHSA-6qxp-vccf-f47h (high) in `` @modelcontextprotocol/sdk@1.30.1 ``, direct, fixed in `` 1.31.0 ``, advisory summary: "MCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP server" https://osv.dev/vulnerability/GHSA-6qxp-vccf-f47h
  - GHSA-5v7r-6r5c-r473 (moderate) in `` file-type@20.5.0 ``, direct, fixed in `` 21.3.1 ``, advisory summary: "file-type affected by infinite loop in ASF parser on malformed input with zero-size sub-header" https://osv.dev/vulnerability/GHSA-5v7r-6r5c-r473
  - GHSA-j47w-4g3g-c36v (moderate) in `` file-type@20.5.0 ``, direct, fixed in `` 21.3.2 ``, advisory summary: "file-type: ZIP Decompression Bomb DoS via \[Content\_Types\].xml entry" https://osv.dev/vulnerability/GHSA-j47w-4g3g-c36v

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0.

## Remotes

- https://mcp.getfrenchie.dev (streamable-http, auth api_key ${FRENCHIE_SKILL_TOKEN}, reachable true, uptime30d 1)

## Packages

- npm @lab94/frenchie@0.5.0 secrets: FRENCHIE_API_KEY

## Tools (7)

- `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.
- `fetch_result_file`: 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.
- `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.
- `get_job_result`: Fetch the latest async Frenchie job result
- `ocr_to_markdown`: Convert PDF/image files into Markdown through Frenchie
- `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.
- `upload_file`: 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.