About ocr
Auto-Reader OCR is an MCP server for extracting and translating text from images and PDFs, with a focus on Arabic and document workflows. It also returns structured fields and RAG-ready markdown or chunks; the first call provisions a trial key.
Key features
- 01Arabic-aware OCR and layout handling
- 02Japanese manga-aware OCR
- 03Automatic detection across 13+ languages
- 04Translation across 100+ languages
- 05Structured document fields with confidence
- 06Markdown and semantic chunk output
Use cases
- 01Extract text from Arabic scans
- 02Translate text in documents
- 03Read invoice, receipt, and ID fields
- 04Prepare scanned documents for RAG
MCP support
The hosted MCP endpoint exposes OCR, document extraction, translation, combined OCR and translation, usage reporting, and API-key creation tools.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://api.auto-reader.com/mcpclaude mcp add --transport http com-auto-reader-ocr https://api.auto-reader.com/mcp{"mcpServers":{"com-auto-reader-ocr":{"type":"http","url":"https://api.auto-reader.com/mcp"}}}Open in Cursor{"servers":{"com-auto-reader-ocr":{"type":"http","url":"https://api.auto-reader.com/mcp"}}}Open in VS Code{"mcpServers":{"com-auto-reader-ocr":{"type":"http","url":"https://api.auto-reader.com/mcp"}}}{"mcpServers":{"com-auto-reader-ocr":{"serverUrl":"https://api.auto-reader.com/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
7| Parameter | Type | Required | Description |
|---|---|---|---|
| lang | string | No | Language hint; default auto. |
| preset | enum | No | Built-in schema. Use zatca for Saudi e-invoices (adds QR validation).invoice | receipt | id | zatca |
| schema | object | No | 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"}. |
| api_key | string | No | Optional Auto-Reader OCR key (nsk_live_...). If omitted, a free trial key is auto-provisioned and returned to you in the result. |
| image_base64 | string | Yes | The document image as base64 (data: URI prefix accepted). |
Details
From the project READMEAuto-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 "[email protected]" -F "lang=auto"
- Machine manifest: https://api.auto-reader.com/llms.txt
- OpenAPI: https://api.auto-reader.com/openapi.json
Idempotency-Keyheader honored; 402 responses carry abuy_directlink.- 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/markdownreturns a raw .md body.extract_documentreturns{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
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.