Look twice.Find the gem.

AI agents and MCP servers, each published with its source and what the checks found.

Marketplace

  • Everything
  • AI agents
  • Apps
  • MCP servers
  • Templates
  • What people want
  • What changed this week
  • The verification standard
  • The ooruby Index
  • Servers that publish no source
  • Reliability guides
  • What the catalogue holds
  • Sell here

Our library

  • Everything, in one place
  • Guides
  • Glossary
  • Calculators
  • Checklists and cheat sheets
  • Community

ooruby

  • Home
  • For teams
  • Site status
  • Company projects
  • RSS feed

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.

AI agentsAppsMCP serversTemplatesWantedCommunityOur library
Sign inSell
Catalogue/Apps/Mistral Ocr

Mistral Ocr

rhk · App

Mistral OCR turns PDFs into Markdown, DOCX or both by sending them to Mistral's OCR service. It writes the text page by page, extracts images to a folder and remaps the image references to local files. A command line and a JavaScript and TypeScript library are included, with a batch mode that uses Mistral's batch inference endpoint and waits for the job by default. The DOCX output focuses on headings, paragraphs and images and does not try to reproduce the original layout.

Written by ooruby from the README of mistral-ocr 0.1.3.

Not claimed by its maker. Is this yours? Prove it and answer the findings

Why it's useful

A PDF becomes Markdown or a Word file with its images pulled out, from a command or from your own code.

What you could do with it

  1. 1Convert a PDF to Markdown and a Word file, with its images saved in a folder beside them.
  2. 2Submit a batch of PDFs without waiting and collect one Markdown and DOCX pair for each later.
  3. 3Ask for structured document annotations with a JSON schema, such as a compact summary of the document.

Written from its documentation: what it says it can do, not what our checks found.

MOappData & analytics

Maintenance

Not measured

No release date is on record for this package yet. The nightly publisher check records one as it reaches each npm package, about once every ten nights.

Release activity only: it says nothing about quality or safety, and a finished small package can be fine without releases. How it is measured

Not yet tested
Data handling disclosed
finding
no statement of what it reads, writes or sends (README.md)

Published because it was found. A finding is information about where the limits are, not a verdict that the software is unsafe.

What this does not cover

  • ·Everything. Treat it as you would software from anywhere else.

Receipt history: every signed receipt for every version of this listing, and what changed between them.

In its maker's words

PDF to Markdown and DOCX conversion powered by Mistral OCR.

Compare with

  • Tobilu Qmdside by side
  • Vectraside by side
  • Tokentracker CLIside by side
Compare all 4

How far this has been checked

Static scanned

What it establishes
Its published package, or for a hosted server its source repository at a recorded commit, was read file by file, without running it, by every check in our current scan.
What it does not
How it behaves when it runs, or anything the scan does not read yet: several rubric checks, the repository's history, and compiled code in folders named dist or build. For a hosted server, that the endpoint runs the code that was read. The ooruby Index sets out exactly what was read.
Exactly what was read
Version 0.1.3, the file with digest sha512-Ugo17A5Pb0HHUZ7LAA3fm1lpYDm5/G6F68zn2qe/5xt9iLeYVHOU8/SxeXKVTPyyWblBbFCn/4tmnODtd2FovQ==, as the registry publishes it. A published version cannot be replaced, so this names the same bytes for anyone who checks.
Authentication
Runs locally. No hosted endpoint is listed for this package. You run it on your own machine, so there is no endpoint of ours to authenticate against.
How the rungs work

Adding it

Run it with:

npx -y mistral-ocr@0.1.3

Pinned to 0.1.3, which is the version the findings above were found in. Drop the version to take whatever is newest, and the report on this page stops describing what you installed.

Where this came from

Registry
npm
Package
mistral-ocr
Version read
0.1.3
Resolved
2026-10-10
Open the source(opens in a new tab)

Built from source, attested

npm publishes a signed statement that this exact package was built from the repository below, at this commit. It is verifiable without taking our word for it.

Repository
github.com/rhanka/mistral-ocr
Commit
ff7f23e198db
Built by
github.com/actions/runner/github-hosted
Registry publish attestation
signed by npm · 2026-10-10
Checked
2026-10-10

The badge, if this is your listing

It renders the current rung (static scanned) and links back here, where what that does and does not establish is one click away. It updates itself as the evidence deepens.

[![ooruby: static scanned](https://ooruby.com/api/badge/mistral-ocr)](https://ooruby.com/market/mistral-ocr)

About this listing

Kind
App
Category
Data & analytics
Pricing
Free
Sandbox
No
Hosted
No
Updated
2026-10-10
Price
Free
Get it freeVisit maker
Rating
no reviews yet
0 want this so far
Sign in to vote

Sign in to watch this listing and hear when its version, rung or findings change.

Similar apps

All apps
TQappData & analytics
4 findingsStatic scanned
Combines BM25 full-text search, vector search and LLM reranking, all run locally with GGUF models. Use it from the command line, as a Node.js library or through MCP tools for your agent.

Tobilu Qmd

tobilu
Free

Indexes your Markdown notes and docs locally, then searches them by keyword, meaning or both.

165k installs/moMIT
VEappData & analytics
5 findingsStatic scanned
Each index is a folder on disk, or IndexedDB in the browser. Queries use cosine similarity with MongoDB-style metadata filters, and local Hugging Face models can embed text without an API key.

Vectra

stevenic
Free

Adds a local, file-backed vector database to Node.js and browser apps for similarity search.

147.4k installs/moMIT
AAappData & analytics
4 findingsStatic scanned
Events carry your own user IDs, so AI usage sits in the same funnels, cohorts and retention charts as product events. You can send full content, metadata only or your own labels.

Amplitude AI

amplitude
Free

Records each turn of your AI feature as an Amplitude event, with model, tokens, cost and latency.

60.4k installs/moMIT

Verification records what our published tests found on a specific version at a specific date. It is not a warranty, and it does not certify that software is free of defects.