mcp server

auto-reader-ocr

Arabic-first OCR, translation & document extraction API — MCP server for Claude Code & agents. Keyless: first call mints a free trial key.

Samqra/auto-reader-ocrcommunitylistedunreviewed

Use tool

Set up

Hosted by its author. Add the URL to your agent — nothing to install.

~/Library/Application Support/Claude/claude_desktop_config.json

Settings → Connectors → Add custom connector

Name: auto-reader-ocr
URL:  https://api.auto-reader.com/mcp

same format Cursor, GitHub Copilot CLI, Junie, JetBrains AI Assistant, Augment (Auggie CLI), Factory Droid, Kiro, Devin CLI +12

Values in angle brackets are placeholders. Restart Claude Desktop after editing its config.Claude Desktop docs

README

synced Oct 17, 2026

Auto-Reader OCR — Arabic-first OCR & Document AI for agents

Extract text from images and PDFs (best-in-class Arabic, manga-aware Japanese, 13+ languages auto-detected), translate 100+ languages, pull structured fields from invoices/receipts/IDs — with Saudi ZATCA e-invoice QR validation — and get RAG-ready markdown or semantic chunks. Self-hosted, PDPL-compliant: documents are processed transiently and never stored.

No signup needed. Your first call auto-provisions a free trial key.

Add to Claude Code (10 seconds)

claude mcp add --transport http auto-reader-ocr https://api.auto-reader.com/mcp

Registry: com.auto-reader/ocr · Tools: ocr_image, extract_document, translate_text, ocr_and_translate, get_usage, create_api_key.

Or plain HTTP (any agent, any language)

curl -X POST https://api.auto-reader.com/signup      # -> {"api_key":"nsk_live_..."}
curl -X POST https://api.auto-reader.com/v1/ocr \
  -H "Authorization: Bearer $KEY" -F "file=@page.png" -F "lang=auto"

Machine manifest: https://api.auto-reader.com/llms.txt
OpenAPI: https://api.auto-reader.com/openapi.json
Idempotency-Key header honored; 402 responses carry a buy_direct link.
Free tier: 250 pages/day with an email, 25/day keyless. Credits never expire.

Why agents pick this API

Arabic is the differentiator: RTL-aware layout, logical-order text, RTL-correct word boxes, Arabic-Indic digits — plus Arabic↔English code-switched documents.
format=markdown / format=chunks (title-bounded, tables kept whole) turn any scan into RAG input in one call; Accept: text/markdown returns a raw .md body.
extract_document returns {value, confidence, box} per field, sourced from OCR geometry — never model guesswork.

Site: https://ocr.auto-reader.com · العربية: https://ocr.auto-reader.com/ar