Frenchie MCP server
io.github.Lab94/frenchie-skillLab94streamable-httpv0.5.0Scanned
OCR, transcription, file extraction, and image generation for AI agents via MCP.
7 tools: 5 change things and 2 only read.
- Reads private data · 1
- Reads text others write · 7
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
5 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the Frenchie MCP server can do
The Frenchie MCP server is published by the GitHub account Lab94. It has 7 tools. It can create or change data (5 tools: ocr_to_markdown, transcribe_to_markdown, generate_image, extract_to_markdown and 1 more), but cannot delete data. 2 tools only read.
1 tool reads private data (fetch_result_file); 7 tools bring in text other people can write (ocr_to_markdown, transcribe_to_markdown, generate_image and 4 more).
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 16, 2026, version 0.5.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
7 tools
Changes things 5Claude Code: ask
extract_to_markdownExtract structured documents (.docx, .xlsx, .csv, .tsv, .pptx) into Markdown through Frenchie.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Extract to Markdown
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
generate_imageGenerate a single image from a text prompt through Frenchie.Reads text others writeNo findings
Why it is in this group
- The name "generate_image" says "generate": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Generate Image
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
ocr_to_markdownConvert PDF/image files into Markdown through FrenchieReads text others writeNo findings
Why it is in this group
- The description's first verb is "convert": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Convert PDF/image files into Markdown through Frenchie
Annotations the server declares
- title: OCR to Markdown
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
transcribe_to_markdownConvert audio/video files into Markdown transcripts through Frenchie.Reads text others writeNo findings
Why it is in this group
- The description's first verb is "convert": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Transcribe to Markdown
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
upload_fileGet a presigned upload URL for use with ocr_to_markdown, transcribe_to_markdown, or extract_to_markdown in HTTP mode.Reads text others writeNo findings
Why it is in this group
- The name "upload_file" says "upload": a word for a change.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it 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.
Annotations the server declares
- title: Upload File (HTTP)
- readOnlyHint: false
- destructiveHint: false
- idempotentHint: false
- openWorldHint: true
Only reads 2Show 2 read-only tools
fetch_result_fileGet a temporary download URL for a result file from OCR/transcription output.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "fetch_result_file" says "fetch": a word for reading.
What it can reach
- private-dataThe name "fetch_result_file" says "fetch" and "file": it reads files.
- private-dataThe description's first sentence says "get" and "file": it reads files.
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
- untrusted-inputThe description's first sentence says "get" and "url": it reads web pages, which anyone can write.
Description, as the server wrote it 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.
Annotations the server declares
- title: Fetch Result File (HTTP)
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
get_job_resultFetch the latest async Frenchie job resultReads text others writeNo findings
Why it is in this group
- The name "get_job_result" says "get": a word for reading.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Fetch the latest async Frenchie job result
Annotations the server declares
- title: Get Job Result
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged outbound.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write7
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:58 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 5
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 5 tools that change things (5 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://mcp.getfrenchie.dev: tools/list returned 7 tools to an anonymous client, including ocr_to_markdown (write), transcribe_to_markdown (write), generate_image (write), extract_to_markdown (write), upload_file (write)
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 0.5.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http frenchie-skill https://mcp.getfrenchie.dev --header 'Authorization: <your-authorization>'claude mcp add --transport http frenchie-skill https://mcp.getfrenchie.dev --header 'Authorization: <your-authorization>'Run in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__frenchie-skill__get_job_result",
"mcp__frenchie-skill__fetch_result_file"
],
"ask": [
"mcp__frenchie-skill__ocr_to_markdown",
"mcp__frenchie-skill__transcribe_to_markdown",
"mcp__frenchie-skill__generate_image",
"mcp__frenchie-skill__extract_to_markdown",
"mcp__frenchie-skill__upload_file"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as frenchie-skill. Review it before you use it.
Capability tags behind 7 rules
- mcp__frenchie-skill__ocr_to_markdown untrusted-input
- mcp__frenchie-skill__transcribe_to_markdown untrusted-input
- mcp__frenchie-skill__generate_image untrusted-input
- mcp__frenchie-skill__extract_to_markdown untrusted-input
- mcp__frenchie-skill__get_job_result untrusted-input
- mcp__frenchie-skill__upload_file untrusted-input
- mcp__frenchie-skill__fetch_result_file private-data, untrusted-input
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/io.github.Lab94/frenchie-skill/verify?hash=6bfbd08a9b7ec7b5f5569060de8d07fb6c7493cb55f8aa4bec7bf4cb7f2ccc14" | jq -e '.changed == false'Pinned hash 6bfbd08a9b7e, from Nov 16, 2026, 00:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/io.github.Lab94/frenchie-skill/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/io.github.Lab94/frenchie-skill)Source: MCP Registry · repository. Synced Oct 21, 2026, 18:17 UTC.
Frenchie MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the Frenchie MCP server safe?
- No scan can promise that. What its definitions show: 7 tools, 5 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the Frenchie MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the Frenchie MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the Frenchie MCP server have?
- 7 tools: 5 write, 2 read. ocr_to_markdown, transcribe_to_markdown, generate_image, extract_to_markdown, upload_file, get_job_result and fetch_result_file.
Does the Frenchie MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the Frenchie MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the Frenchie MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 16, 2026.