OCR MCP Server

by auto-reader Your server? Claim it

answering

OCR is answering right now. Last checked 13 min ago. It exposes 7 tools. Last commit 1 Aug 2026.

Arabic-first OCR, translation and document extraction. First call mints a free trial key.

Uptime history 91 days of history · worst day 93%

91 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

126 ms

Response time

average over 24h

Stars

last commit 1 Aug 2026

What changed 4

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 22 August 2026. No other catalogue keeps this.

3 Sep a tool description was rewritten read_manga

3 Sep a tool changed the parameters it asks for read_manga

29 Aug a tool changed the parameters it asks for ocr_image

22 Aug a tool appeared read_manga

OCR missed one check this week

Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 13 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

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

Settings → Connectors → Add custom connector, then paste this address

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

~/.codex/config.toml

[mcp_servers.ocr]
url = "https://api.auto-reader.com/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "ocr": {
      "url": "https://api.auto-reader.com/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "ocr": {
      "type": "http",
      "url": "https://api.auto-reader.com/mcp"
    }
  }
}

Available tools 7

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

ocr

ocr_and_translate

One call: OCR an image, then translate every line into target_lang. Arabic-first OCR and manga-aware Japanese with right-to-left-aware layout, followed by LLM translation. Automatic source-language detection. Provide the image as base64. Ideal for reading foreign documents, signs, manga, or receipts end-to-end in a single step.

ocr_image

Extract text from an image with GPU OCR. Best-in-class Arabic (plus Persian/Urdu) accuracy, manga-aware vertical Japanese, and strong English, French, Spanish, German, Chinese, Korean, Russian, Italian and Portuguese — 13+ languages. Automatic language and script detection with lang="auto". Returns reading-order layout text (right-to-left aware, paragraph-gapped) that is ready to feed an LLM or show a human, plus the detected language, the engine used, and the number of text blocks found. Provide the image as base64. Use the mode hint (document | receipt | manga | scene) to tune detection.

api

create_api_key

Provision a new Auto-Reader OCR API key instantly, with no human steps. Pass an optional email to unlock the larger free tier (about 250 credits/day, vs about 25/day for an email-less trial key). Store the returned key and pass it as api_key on future calls.

extract

extract_document

Extract STRUCTURED FIELDS from a document image: invoices, receipts, ID cards — or any custom JSON schema you supply. Every field returns {value, confidence, box} where the confidence and box come from the OCR geometry (never model guesswork); absent fields are null. preset="zatca" additionally decodes the Saudi ZATCA e-invoice QR (TLV) and cross-validates it against the printed fields — use it for Saudi tax invoices. Arabic-first accuracy. 5 credits/page (zatca 7).

manga

read_manga

OCR a comic/manga page, routed by LANGUAGE (not the blanket "manga = Japanese" assumption). Japanese goes to the manga specialist reader that reads vertical, hand-lettered speech bubbles in right-to-left order; Korean manhwa, Chinese manhua and other scripts use their own OCR pack; low-confidence pages escalate to the vision model. Returns text blocks in reading order plus the detected language, the engine used, and whether the page is vertical. Provide the image as base64. Pass lang explicitly (ko/zh/...) for the best non-Japanese result; default "auto" detects it.

translate

translate_text

Translate text between 13+ languages with an LLM. Arabic-first quality, with formality control (formal/informal) and optional context to disambiguate meaning. Handles both short dictionary-style word lookups and full documents. Returns the translation and, when available, alternative phrasings.

usage

get_usage

Check your Auto-Reader OCR key: tier, remaining daily free credits, prepaid credit balance, subscription allowance, and per-minute rate limit. Use it to throttle yourself before hitting a limit.

Endpoints

URL	Transport	State	Latency	Checked
https://api.auto-reader.com/mcp	streamable-http	answering	88 ms	13 min ago

Alternatives to OCR

same job, measured the same way

ScribeTools

by scribetools

OCR, editable Word, tables, translation and data extraction for Arabic-script documents

answering

Docu-Scan MCP

by spocont

PDF and document extraction via Google Document AI. Free trial available.

answering

Document Processing

by filegraph

Extract text from documents, manipulate PDFs, and perform OCR on images.

9 tools answering

Frenchie

by lab94

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

74 installs/wk 7 tools answering

Techtenstein PDF

by sathvic-kollu

PDF text and table extraction plus metadata. Supports OCR for scanned documents.

77 installs/wk local only

Rq Scan

by recerqa

MCP Server for RQ-SCAN - AI-powered document OCR and data extraction platform

37 installs/wk local only

Faceabot Translate

by faceabot

Translate text or a document into about 100 languages. Free, no key.

1 tools answering

Mistral MCP

by swih

Mistral MCP server: extract invoices and documents from text, Markdown or OCR into typed JSON.

182 installs/wk local only

OCR — questions

Answers built from our own checks of this server.

What can OCR do?

It exposes 7 tools, read directly from the server on our last check. Among them: create_api_key, extract_document, get_usage, ocr_and_translate, ocr_image, read_manga and 1 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is OCR working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 126 ms. The bar chart above shows every period we have measured.

How do I connect OCR?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does OCR need an API key?

No. OCR completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 7 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is OCR?

It answers our handshake in 126 ms on average, which is faster than 87% of all working MCP servers we measure. That puts it in the quick quarter of the ecosystem. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is OCR open source?

The code is open source: it is published under the MIT licence and 0 stars on GitHub. The licence covers the code in the repository, not the hosted service at api.auto-reader.com, which runs on its operator's own terms.