AI Tools

Scanned PDF OCR to Markdown

Convert scanned or image-heavy PDFs into Markdown with OpenDataLoader hybrid OCR, with a graceful fallback when the hybrid backend is unavailable

file· File resultOpen tool

Quick start

Call this tool from your code in three languages.

cURL

# 1) Upload each file first → returns { filePath }
curl -X POST 'https://api.elysiatools.com/upload/scanned-pdf-ocr-to-markdown' \
  -F 'file=@/path/to/pdfFile.ext'

# 2) Call the tool with the returned filePath values
curl -X POST 'https://api.elysiatools.com/en/api/tools/scanned-pdf-ocr-to-markdown' \
  -F 'pdfFile=/public/samples/pdf/pdf-ocr-text-layer-example1.pdf' \
  -F 'pages=' \
  -F 'keepLineBreaks=true' \
  -F 'includePageSeparators=true' \
  -F 'hybridBackendUrl=' \
  -F 'preferHybridOcr=false'

API reference

Send a POST request with your inputs as JSON. File parameters require a separate upload first.

Endpoint

HTTP

POST https://api.elysiatools.com/en/api/tools/scanned-pdf-ocr-to-markdown

Parameters

Name	Type	Required	Description
pdfFile	fileupload required	Yes	—
pages	text	No	—
keepLineBreaks	checkbox	No	—
includePageSeparators	checkbox	No	—
hybridBackendUrl	text	No	—
preferHybridOcr	checkbox	No	—

File-type parameters must be uploaded first via POST /upload/scanned-pdf-ocr-to-markdown, then the returned filePath is passed to the corresponding file field.

Response format

File result

JSON

{
  "filePath": "/public/processing/randomid.ext",
  "fileName": "output.ext",
  "contentType": "application/octet-stream",
  "size": 1024,
  "metadata": {
    "key": "value"
  },
  "error": "Error message (optional)",
  "message": "Notification message (optional)"
}

MCP integration

Add this tool to your Model Context Protocol server so AI agents can list and call it.

Server configuration

Add this block to your MCP client configuration:

mcp.json

{
  "mcpServers": {
    "elysiatools-scanned-pdf-ocr-to-markdown": {
      "name": "scanned-pdf-ocr-to-markdown",
      "description": "Convert scanned or image-heavy PDFs into Markdown with OpenDataLoader hybrid OCR, with a graceful fallback when the hybrid backend is unavailable",
      "baseUrl": "https://api.elysiatools.com/mcp/sse?toolId=scanned-pdf-ocr-to-markdown",
      "command": "",
      "args": [],
      "env": {},
      "isActive": true,
      "type": "sse"
    }
  }
}

List available tools

After connecting to the SSE endpoint, list the exposed tools:

tools/list

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/list"
}

Call this tool

Invoke the tool by its id, passing arguments built from its parameters:

tools/call

{
  "jsonrpc": "2.0",
  "id": 2,
  "method": "tools/call",
  "params": {
    "name": "scanned-pdf-ocr-to-markdown",
    "arguments": {
  "pdfFile": "/public/samples/pdf/pdf-ocr-text-layer-example1.pdf",
  "pages": "",
  "keepLineBreaks": true,
  "includePageSeparators": true,
  "hybridBackendUrl": "",
  "preferHybridOcr": false
}
  }
}

Chain multiple tools in one session with a comma-separated toolId list, e.g. /mcp/sse?toolId=png-to-webp,jpg-to-webp,gif-to-webp (max 20).

File parameters accept a public file URL only (https://…). Local paths, data: URIs, and Base64 strings are not supported.

Questions or issues? Contact [email protected]