Document Tools

OCR PDF to Structured JSON Bridge

Extract the PDF text layer with geometry (lines by y-position, tables by column gaps, headings by font size, colon key-value pairs), then fill a user-supplied JSON Schema field by field — labels matched by normalized keys, values coerced to declared types and validated with ajv.

html· HTML resultOpen tool

Quick start

Call this tool from your code in three languages.

cURL

# 1) Request a presigned URL → returns { uploadUrl, storageKey }
curl -X POST 'https://api.elysiatools.com/api/upload/presign/ocr-pdf-to-structured-json-bridge' \
  -H 'Content-Type: application/json' \
  -d '{"filename":"pdfFile.ext","contentType":"application/octet-stream","size":12345}'

# 2) PUT the file bytes directly to the presigned uploadUrl
curl -X PUT '<presigned uploadUrl>' \
  --data-binary @/path/to/file.ext

# 3) Call the tool, passing the returned storageKey for each file field
curl -X POST 'https://api.elysiatools.com/en/api/tools/ocr-pdf-to-structured-json-bridge' \
  -F 'pdfFile=uploads/2026/01/01/your-tool-1700000000000-abc123.ext' \
  -F 'schemaInput={
  "type": "object",
  "properties": {
    "invoice_number": { "type": "string" },
    "invoice_date": { "type": "string", "format": "date" },
    "customer": { "type": "string" },
    "currency": { "type": "string", "enum": ["USD", "EUR"] },
    "total": { "type": "number" }
  },
  "required": ["invoice_number", "total"]
}' \
  -F 'numberStyle=auto'

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/ocr-pdf-to-structured-json-bridge

Parameters

Name	Type	Required	Description
pdfFile	fileupload required	Yes	—
schemaInput	textarea	Yes	—
numberStyle	select	Yes	—

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

Response format

HTML result

JSON

{
  "result": "<div>Processed HTML content</div>",
  "error": "Error message (optional)",
  "message": "Notification message (optional)",
  "metadata": {
    "key": "value"
  }
}

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-ocr-pdf-to-structured-json-bridge": {
      "name": "ocr-pdf-to-structured-json-bridge",
      "description": "Extract the PDF text layer with geometry (lines by y-position, tables by column gaps, headings by font size, colon key-value pairs), then fill a user-supplied JSON Schema field by field — labels matched by normalized keys, values coerced to declared types and validated with ajv.",
      "baseUrl": "https://api.elysiatools.com/mcp/sse?toolId=ocr-pdf-to-structured-json-bridge",
      "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": "ocr-pdf-to-structured-json-bridge",
    "arguments": {
  "pdfFile": "https://example.com/file.ext",
  "schemaInput": "{\n  \"type\": \"object\",\n  \"properties\": {\n    \"invoice_number\": { \"type\": \"string\" },\n    \"invoice_date\": { \"type\": \"string\", \"format\": \"date\" },\n    \"customer\": { \"type\": \"string\" },\n    \"currency\": { \"type\": \"string\", \"enum\": [\"USD\", \"EUR\"] },\n    \"total\": { \"type\": \"number\" }\n  },\n  \"required\": [\"invoice_number\", \"total\"]\n}",
  "numberStyle": "auto"
}
  }
}

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]