com.auto-reader/ocr (MCP) Server

The MCP server com.auto-reader/ocr provides Arabic-first OCR for images and PDFs, plus translation and document extraction. It auto-detects Japanese and 13+ languages, extracts structured fields from invoices/receipts/IDs, and supports RAG-ready output formats. It also includes Saudi ZATCA e-invoice QR validation.

🛠️ Key Features

Arabic-first OCR for images and PDFs
Auto-detection covering Japanese and 13+ languages
Translation across 100+ languages
Structured field extraction for invoices, receipts, and IDs
ZATCA e-invoice QR validation
RAG-ready markdown or semantic chunks
Self-hosted, PDPL-compliant processing (transient; documents not stored)

🚀 Use Cases

Converting Arabic documents in images/PDFs into text
Translating extracted content into 100+ languages
Invoice/receipt/ID data extraction for downstream processing
Preparing OCR results for RAG workflows

⚡ Developer Benefits

Designed for AI agents via an MCP server (mcp-server)
Provides RAG-ready markdown or semantic chunks
Supports related domains: invoice-extraction, translation, rag, ocr, pdf, api

⚠️ Limitations

Includes a “first call” flow that auto-provisions a free trial key (first call required)

{ "type": "object", "properties": { "image_base64": { "type": "string", "description": "The document image as base64 (data: URI prefix accepted)." }, "preset": { "type": "string", "enum": [ "invoice", "receipt", "id", "zatca" ], "description": "Built-in schema. Use zatca for Saudi e-invoices (adds QR validation)." }, "schema": { "type": "object", "description": "Custom extraction schema instead of a preset: an object whose keys are the fields you want, values describing them, e.g. {\"policy_number\": \"string|null\"}." }, "lang": { "type": "string", "description": "Language hint; default auto.", "default": "auto" }, "api_key": { "type": "string", "description": "Optional Auto-Reader OCR key (nsk_live_...). If omitted, a free trial key is auto-provisioned and returned to you in the result." } }, "required": [ "image_base64" ] }

{ "type": "object", "properties": { "image_base64": { "type": "string", "description": "The image encoded as base64 (a data: URI prefix is accepted and stripped)." }, "lang": { "type": "string", "description": "Language/script hint. Default \"auto\" detects it. Codes: ar, fa, ur, en, fr, es, de, ja, zh, ko, ru, it, pt.", "default": "auto" }, "mode": { "type": "string", "enum": [ "document", "receipt", "manga", "scene" ], "description": "Content hint that tunes detection and prompts. Default \"document\".", "default": "document" }, "api_key": { "type": "string", "description": "Optional Auto-Reader OCR key (nsk_live_...). If omitted, a free trial key is auto-provisioned and returned to you in the result." } }, "required": [ "image_base64" ] }

{ "type": "object", "properties": { "text": { "type": "string", "description": "The text to translate." }, "target_lang": { "type": "string", "description": "Target language, as a name or code (e.g. English, Arabic, ar, ja, fr)." }, "formality": { "type": "string", "enum": [ "formal", "informal" ], "description": "Optional register for the output." }, "context": { "type": "string", "description": "Optional background text that improves accuracy (it is not translated)." }, "api_key": { "type": "string", "description": "Optional key (nsk_live_...). Auto-provisioned if omitted." } }, "required": [ "text", "target_lang" ] }

{ "type": "object", "properties": { "image_base64": { "type": "string", "description": "The image encoded as base64 (a data: URI prefix is accepted and stripped)." }, "target_lang": { "type": "string", "description": "Language to translate into, as a name or code (e.g. English, ar, ja)." }, "api_key": { "type": "string", "description": "Optional key (nsk_live_...). Auto-provisioned if omitted." } }, "required": [ "image_base64", "target_lang" ] }

{ "type": "object", "properties": { "email": { "type": "string", "description": "Optional email to attach for the larger free tier and a verification link." } }, "required": [] }

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.

Or plain HTTP (any agent, any language)

bash

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.

Install

Tools (6)

extract_documentocr_imagetranslate_textocr_and_translateget_usagecreate_api_key

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://api.auto-reader.com/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "ocr": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://api.auto-reader.com/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

com.auto-reader/ocr