Hebrew and English OCR for PDFs and images: text, key fields and tables, page by page.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
OCR-AI API key as a Bearer token: Bearer ocrai_sk_...
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
Return a Stripe Checkout link for a page pack. Give the link to your user: they pay in their browser, and the pages are added to this key's account as soon as the payment completes. This tool never charges anything by itself.
p100: 100 pages ($9 / ₪29); p500: 500 pages ($29 / ₪99); p2000: 2000 pages ($89 / ₪299)
Default: USD.
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http ocr-ai https://ocr-ai.com/mcp \ --header 'Authorization: Bearer YOUR_TOKEN'
Headers
Authorization (required): OCR-AI API key as a Bearer token: Bearer ocrai_sk_...Return a Stripe Checkout link for a page pack. Give the link to your user: they pay in their browser, and the pages are added to this key's account as soon as the payment completes. This tool never charges anything by itself.
| Argument | Type | Description |
|---|---|---|
| pack* | string | p100: 100 pages ($9 / ₪29); p500: 500 pages ($29 / ₪99); p2000: 2000 pages ($89 / ₪299) |
| currency | string | Default: USD. |
{
"type": "object",
"required": [
"pack"
],
"properties": {
"pack": {
"enum": [
"p100",
"p500",
"p2000"
],
"type": "string",
"description": "p100: 100 pages ($9 / ₪29); p500: 500 pages ($29 / ₪99); p2000: 2000 pages ($89 / ₪299)"
},
"currency": {
"enum": [
"USD",
"ILS"
],
"type": "string",
"description": "Default: USD."
}
},
"additionalProperties": false
}How many pages the API key's account can still read, and a link where the user can add pages.
No arguments.
{
"type": "object",
"properties": {},
"additionalProperties": false
}Read a PDF or an image (JPEG, PNG, WebP) and return its text, its key fields (vendor, dates, totals, VAT, ids…) and its tables, page by page. Built for Hebrew and English documents, including mixed right-to-left lines. Costs one page from the key's account per page read; a page that fails is not charged. Up to 20 pages per call: read longer PDFs in ranges with "pages". A call of many pages can take more than a minute. Pages your client stops waiting for may still be charged, so if a call times out, read smaller ranges, for example 5 pages per call.
| Argument | Type | Description |
|---|---|---|
| hint | string | What the document is, if known. Default: auto. |
| pages | string | PDF pages to read, for example "1-5,8". Default: from page 1, up to the per-call limit. |
| file_url | string | A public https URL of the document. Use this or file_base64. |
| language | string | Language of the field labels and summary in the result. Default: en. |
| file_base64 | string | The document's bytes, base64-encoded. Use this or file_url. |
{
"type": "object",
"properties": {
"hint": {
"enum": [
"auto",
"invoice",
"receipt",
"card",
"table",
"text"
],
"type": "string",
"description": "What the document is, if known. Default: auto."
},
"pages": {
"type": "string",
"description": "PDF pages to read, for example \"1-5,8\". Default: from page 1, up to the per-call limit."
},
"file_url": {
"type": "string",
"description": "A public https URL of the document. Use this or file_base64."
},
"language": {
"enum": [
"en",
"he"
],
"type": "string",
"description": "Language of the field labels and summary in the result. Default: en."
},
"file_base64": {
"type": "string",
"description": "The document's bytes, base64-encoded. Use this or file_url."
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 4, 2026.