Media

PDF Image & Caption Extractor

Extract images from PDFs, match nearby captions, and generate an HTML index package using OpenDataLoader

html· HTML 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/pdf-image-caption-extractor' \
  -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/pdf-image-caption-extractor' \
  -F 'pdfFile=/public/samples/pdf/pdf-image-caption-extractor-source-example1.pdf' \
  -F 'imageFormat=png' \
  -F 'pages=' \
  -F 'useStructTree=true'

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/pdf-image-caption-extractor

Parameters

Name	Type	Required	Description
pdfFile	fileupload required	Yes	—
imageFormat	select	No	—
pages	text	No	—
useStructTree	checkbox	No	—

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

Response format

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-pdf-image-caption-extractor": {
      "name": "pdf-image-caption-extractor",
      "description": "Extract images from PDFs, match nearby captions, and generate an HTML index package using OpenDataLoader",
      "baseUrl": "https://api.elysiatools.com/mcp/sse?toolId=pdf-image-caption-extractor",
      "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": "pdf-image-caption-extractor",
    "arguments": {
  "pdfFile": "/public/samples/pdf/pdf-image-caption-extractor-source-example1.pdf",
  "imageFormat": "png",
  "pages": "",
  "useStructTree": true
}
  }
}

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).

Browse tools Open tool