Integration

Cloudmersive OCR integration

Cloudmersive OCR extracts text from scanned images, photos of documents and PDFs: plain text, or words and lines with their position on the page and a confidence level, in about 100 languages. It also reads photos of receipts (business, line items, totals) and business cards (name, title, company, contact details) into structured fields, and detects the rotation angle of a page. Not included: form recognition with field templates, the preprocessing routes that return a modified image, and receipt-to-CSV conversion. Authentication is a Cloudmersive API key sent in the Apikey header; a free-tier key only works once a credit card is added to the account.

Connect Cloudmersive OCR How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Cloudmersive OCR.Built from the 12 Cloudmersive OCR tools below, on the connection you add once.

What you can do with Cloudmersive OCR

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

To text, 3 operations

ocr_image_to_textOcr image to textPOSTConverts a scanned image (JPEG, PNG and other common formats) into text with OCR, with a mean confidence level. Made for scanned documents; use ocr_photo_to_text for phone photos, which unskews the image first.
ocr_pdf_to_textOcr pdf to textPOSTConverts a scanned PDF into text with OCR, page by page with a confidence level per page. A PDF of more than 25 pages runs in the background: the result then carries an AsyncJobID for get_pdf_ocr_job_status.
ocr_photo_to_textOcr photo to textPOSTConverts a photo of a document (for example taken with a smartphone, crooked or with a desk in the frame) into text with OCR. Use ocr_image_to_text for scanned images.

Words with location, 3 operations

ocr_image_to_words_with_locationOcr image to words with locationPOSTConverts a scanned image (JPEG, PNG and other common formats) into words with OCR, each with its position, its line, paragraph and block number, and a confidence level. Made for scanned documents.
ocr_pdf_to_words_with_locationOcr pdf to words with locationPOSTConverts a scanned PDF into words with OCR, page by page, each word with its position on the page and a confidence level.
ocr_photo_to_words_with_locationOcr photo to words with locationPOSTConverts a photo of a document or receipt into words with OCR, each with its position on the page. Made for photos; use ocr_image_to_words_with_location for scanned documents.

Lines with location, 2 operations

ocr_image_to_lines_with_locationOcr image to lines with locationPOSTConverts a scanned image (JPEG, PNG and other common formats) into lines of text with OCR, each line with its words and their positions. Made for scanned documents.
ocr_pdf_to_lines_with_locationOcr pdf to lines with locationPOSTConverts a scanned PDF into lines of text with OCR, page by page, each line with its words and their positions.

Business card, 1 operation

recognize_business_cardRecognize business cardPOSTReads a photo of a business card and extracts the person's name and title, the business name, address, phone number and email address.

Get job statu, 1 operation

get_pdf_ocr_job_statusGet pdf ocr job statusGETReturns the status (STARTED or COMPLETED) of a background PDF OCR job started by ocr_pdf_to_text and, once it is completed, the text of each page.

Get page angle, 1 operation

get_page_angleGet page anglePOSTDetects the rotation angle of the page in a photo or scan of a document, in radians (0 is perfectly horizontal).

Receipt, 1 operation

recognize_receiptRecognize receiptPOSTReads a photo of a receipt and extracts the business name, website, address and phone number, the date and time, the line items, the subtotal and the total.

Use Cloudmersive OCR from Claude Code, Cursor or Codex

Connect Cloudmersive OCR in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Cloudmersive OCR operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Cloudmersive OCR

Create your workspace
Sign up free. Nothing to install.
Connect Cloudmersive OCR once
Add your Cloudmersive OCR connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.