# Frenchie MCP server

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

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-lab94-frenchie-skill
- Repository: https://github.com/Lab94/frenchie-skill
- Website: https://getfrenchie.dev

## Install
- Command: `npx -y @lab94/frenchie`
- Endpoint: https://mcp.getfrenchie.dev
- Auth: Auth required by registry metadata

## Setup notes
- Remote header: Authorization (required; secret)
- Remote header: X-Frenchie-Default-Language
- Package: Npm @lab94/frenchie v0.5.0
- Environment variable: FRENCHIE_API_KEY (required; secret)
- Environment variable: FRENCHIE_DEFAULT_LANGUAGE
- The upstream registry signals required auth or secrets.
- Remote endpoint: https://mcp.getfrenchie.dev
- Header: Authorization
- Header: X-Frenchie-Default-Language

## Tools
- ocr_to_markdown (OCR to Markdown) - Convert PDF/image files into Markdown through Frenchie Endpoint: https://mcp.getfrenchie.dev
- transcribe_to_markdown (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. Endpoint: https://mcp.getfrenchie.dev
- generate_image (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. Endpoint: https://mcp.getfrenchie.dev
- extract_to_markdown (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. Endpoint: https://mcp.getfrenchie.dev
- get_job_result (Get Job Result) - Fetch the latest async Frenchie job result Endpoint: https://mcp.getfrenchie.dev
- upload_file (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. Endpoint: https://mcp.getfrenchie.dev
- fetch_result_file (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. Endpoint: https://mcp.getfrenchie.dev

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.Lab94
- Version: 0.5.0
- Runtime: Npm
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: May 7, 2026
- Source: https://registry.modelcontextprotocol.io