ZBS Index What actually exists in applied AI, with the source next to it

mcp server

Frenchie

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

Description as published by the maintainer. Source

  • version 0.5.0
  • slowing
  • data extraction
  • document understanding
  • image generation

slowing — Registry entry last updated 2026-05-07. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

What this server can do

7 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

extract_to_markdown(api_key, file_path, uploaded_file_reference)
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(api_key, object_key)
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. Required: object_key.
generate_image(size, style, format, prompt, api_key, quality, background, output_dir)
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. Required: prompt.
get_job_result(job_id, api_key)
Fetch the latest async Frenchie job result Required: job_id.
ocr_to_markdown(api_key, file_path, uploaded_file_reference)
Convert PDF/image files into Markdown through Frenchie
transcribe_to_markdown(api_key, language, file_path, uploaded_file_reference)
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(api_key, filename, file_size, mime_type)
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. Required: filename, file_size, mime_type.

Last successful function declaration observed on . Source: https://mcp.getfrenchie.dev. We list what the server declared; we do not call any of these functions.

Endpoint status observed on . Source: https://mcp.getfrenchie.dev.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Signal Value What it measures Window Observed Source
Latest published version 0.5.0 Latest version string the maintainer published to the registry. as of fetch Model Context Protocol
Registry record last updated 2026-05-07 When the registry record was last updated by its maintainer. point in time Model Context Protocol
First listed in the MCP Registry 2026-05-07 Date this server was first published to the official MCP Registry. Not a usage or quality measure. point in time Model Context Protocol
mcp tools declared 7 tools Number of functions the server itself declared when asked to list them. This is what the server offers an agent, not a measure of how well any of them work. as of probe mcp.getfrenchie.dev
mcp endpoint status ok The server listed 7 functions when asked. as of probe mcp.getfrenchie.dev

Where to get it

This record as data

Every field on this page, with its source and observation date, is in the catalog JSON. Fetch the whole kind at once instead of parsing this HTML.

GET /api/v1/entries/mcp_server.json

Sources

  1. Tools declared by the MCP server at https://mcp.getfrenchie.dev — mcp.getfrenchie.dev, observed , trust tier 1.
  2. Official MCP Registry — Model Context Protocol, observed , trust tier 1.