mcpbeat Sign in

Frenchie MCP Server

answering

Frenchie is answering right now. Last checked 3 min ago. 135 installs a week from npm. It exposes 7 tools. Last commit 7 May 2026.

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

Installs per day peak 35 · avg 16 · +104% w/w
a month agotoday
Uptime history 47 days of history · worst day 98%
47 days agonow
100.0%
Uptime 24h
92 of 92 checks
7
Tools
read from the server
579 ms
Response time
average over 24h
135
Installs / week
npm and PyPI

What the code does

We read the source, 18 h ago · tools taken from the live server · rules 3dff92dd89df

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

Runs commands and sends data out [пакет] bin/install.cjs:806
    const out = execFileSync(which, ["npx"], { encoding: "utf8", stdio: ["ignore", "pipe", "ignore"] })
Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

    const out = execFileSync(which, ["npx"], { encoding: "utf8", stdio: ["ignore", "pipe", "ignore"] })
Reads files and sends them to the network bin/install.cjs:489, [пакет] bin/install.cjs:489
  return fs.readdirSync(SKILLS_DIR).filter((name) => {

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Frenchie and you get told the day something new turns up.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 3 min ago.

run in your terminal
claude mcp add frenchie-skill --transport http https://mcp.getfrenchie.dev
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "frenchie-skill": {
      "url": "https://mcp.getfrenchie.dev"
    }
  }
}
~/.codex/config.toml
[mcp_servers.frenchie-skill]
url = "https://mcp.getfrenchie.dev"
.cursor/mcp.json
{
  "mcpServers": {
    "frenchie-skill": {
      "url": "https://mcp.getfrenchie.dev"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "frenchie-skill": {
      "url": "https://mcp.getfrenchie.dev"
    }
  }
}

This one needs environment variables set before it will start: FRENCHIE_API_KEY (Your Frenchie API key (starts with fr_). Create one at https://getfrenchie.dev/dashboard/api-keys — first signup comes with 100 free credits.), FRENCHIE_DEFAULT_LANGUAGE (Optional ISO 639-1 language hint (e.g. 'th', 'en', 'ja') applied to transcribe_to_markdown when the tool input does not specify a language. Tool-level language always wins.). The author declared them in the registry entry; get the values from the project itself.

Available tools 7

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

extract
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.
generate
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.
job
get_job_result
Fetch the latest async Frenchie job result
ocr
ocr_to_markdown
Convert PDF/image files into Markdown through Frenchie
result
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.
transcribe
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
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.

Endpoints

URLTransportStateLatencyChecked
https://mcp.getfrenchie.dev streamable-http answering 559 ms 3 min ago

Alternatives to Frenchie

same job, measured the same way
deAPI MCP Server
by deapi-ai

35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI

answering
Bigapi
by bigapi

File operations for AI agents: PDF, extraction, OCR, images. $0.01/op, 100 free.

515 installs/wk local only
C
Docu-Scan MCP
by spocont

PDF and document extraction via Google Document AI. Free trial available.

answering
Agentrender MCP
by corbinvachal48

URL to screenshot, PDF, or structured extract for AI agents via MCP.

local only
Contendeo
by contendeo

Multimodal video analysis MCP — transcription, vision, and OCR for any video URL.

answering
OCR
by auto-reader

Arabic-first OCR, translation and document extraction. First call mints a free trial key.

7 tools answering
Bynn
by bynn

Document fraud detection for manipulated, fake and AI-generated PDF and image documents.

answering
Ocular Audio MCP
by rayakaan

MCP server for video transcripts, screenshots, and OCR on YouTube and web videos.

44 installs/wk local only

Frenchie — questions

Answers built from our own checks of this server.

What can Frenchie do?
It exposes 7 tools, read directly from the server on our last check. Among them: extract_to_markdown, fetch_result_file, generate_image, get_job_result, ocr_to_markdown, transcribe_to_markdown and 1 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is Frenchie working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 579 ms. The bar chart above shows every period we have measured.
How do I connect Frenchie?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Frenchie need an API key?
No. Frenchie completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 7 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Frenchie?
It answers our handshake in 579 ms on average, which is faster than 23% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
How many people use Frenchie?
The npm package @lab94/frenchie was installed 135 times in the last week. Week over week that is +104%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.
Is Frenchie open source?
Yes — it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.