Ext Ops Panel
Open dashboard
Comparison

Handwriting OCR vs Frenchie

Handwriting OCR is an MCP server published by Handwriting-OCR. Marketplaces we read that list it: 1 (Docker MCP Catalog). Frenchie is an MCP server published by Lab94. Marketplaces we read that list it: 1 (Official MCP Registry). As of our marketplace pass on 2026-10-13. This pair was picked by a reader, not by our comparison rule, so search engines are asked not to index the page.

Where each is published

Where each is published
MarketplaceHandwriting OCRFrenchie
Docker MCP Catalog Listed
Version: sha256:141e2e00e706
Forks (GitHub): 7
Pulls (Docker Hub): 18 829
Stars (Docker Hub): 2
Stars (GitHub): 17
Not marked · First seen
Not listed
Official MCP Registry Not listed Listed
Version: 0.5.0
Downloads/month (npm): 335
Downloads/week (npm): 54
Forks (GitHub): 0
Stars (GitHub): 0
Not marked · First seen

Each figure is the marketplace's own and is never added up across marketplaces. A marketplace that publishes no figure shows none: no number is not zero.

The facts side by side

Handwriting OCR vs Frenchie
FactHandwriting OCRFrenchie
Marketplaces that list it11
Stars (GitHub) (differs)17 (better)0 (worse)
Pulls (Docker Hub) (differs)18 829No figure on Docker Hub
Forks (GitHub) (differs)7 (better)0 (worse)
Last releaseNot publishedNot published
Where it runs (differs)On your machine (mcp/handwriting-ocr)Remote server (mcp.getfrenchie.dev)
Transport (differs)stdioStreamable HTTP
Tools it declares (differs)3Not published
Environment variables it asks for (differs)1, secrets among them: 12, secrets among them: 1
LicenceNot statedNot stated
Repository (differs)github.com/handwriting-ocr/handwriting-ocr-mcp-servergithub.com/lab94/frenchie-skill
Changes in the last 7 days00
First seen2026-10-112026-10-11
Endpoint at the last check (differs)no remote endpoint we checkResponded 4 h ago

Lines where the two differ have a tinted background and bold values. Where the data itself says which value is better (more marketplaces, a larger figure of the same marketplace, a fresher release, a verified mark on a marketplace that lists both), the better one is also marked green with ▲ and the worse one red with ▼. Where it runs, the transport, the tools, the settings, hooks, the bundle's parts, the licence and the week's changes are marked only as different: more or fewer is not better in itself.

What each says it does

Handwriting OCR

In its own words, on Docker MCP Catalog:

Model Context Protocol (MCP) Server for Handwriting OCR.

Frenchie

In its own words, on Official MCP Registry:

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

How to run each

Handwriting OCR As a local MCP server: Docker image

Claude Code
claude mcp add --env "API_TOKEN=<YOUR_API_TOKEN>" --transport stdio handwriting-ocr -- docker run -i --rm -e API_TOKEN mcp/handwriting-ocr

Requires: API_TOKEN (secret)

Frenchie As a remote MCP server

Claude Code
claude mcp add --transport http frenchie-skill https://mcp.getfrenchie.dev --header "Authorization: Bearer <YOUR_TOKEN>"

Requires: FRENCHIE_API_KEY (secret), Authorization header

Commands built only from what the marketplaces declare; the full set for every client is on each card.

Only Frenchie has a remote endpoint we check. How we check endpoints

Tools each declares

The marketplaces of Frenchie publish no list of tools, so we do not compare tools.

Settings each asks for

Only Handwriting OCR asks for

  • API_TOKEN (secret)

Only Frenchie asks for

  • FRENCHIE_API_KEY (secret)
  • FRENCHIE_DEFAULT_LANGUAGE

Settings as each marketplace publishes them. Asking for fewer is not better in itself.

What it can do: Handwriting OCR · What it can do: Frenchie · Compare two other plugins

Data comes from the Docker MCP Catalog (desktop.docker.com/mcp/catalog) and Docker Hub. Data comes from the Official MCP Registry (registry.modelcontextprotocol.io), CC0 1.0. Figures come from our own regular passes over the marketplaces, last read on . We publish no contact details for plugin publishers.

Where the data comes from: how the catalog is built