VOOZH about

URL: https://apify.com/ntriqpro/document-intelligence-mcp

โ‡ฑ Document AI โ€” Extract, Summarize, Classify Files ยท Apify


๐Ÿ‘ Document AI - Extract, Summarize & Classify Files avatar

Document AI - Extract, Summarize & Classify Files

Pricing

Pay per event + usage

Go to Apify Store

Document AI - Extract, Summarize & Classify Files

Automatically read PDFs and documents. Extract text, create summaries, and categorize documents by type.

Pricing

Pay per event + usage

Rating

0.0

(0)

Developer

๐Ÿ‘ daehwan kim

daehwan kim

Maintained by Community

Actor stats

0

Bookmarked

1

Total users

0

Monthly active users

a month ago

Last modified

Share

Document Intelligence MCP Server

Extract text (OCR), summarize, classify, and extract tables from document images using local AI vision models.

Features

ToolDescriptionPrice
extract_textOCR - Extract all text from document images in markdown format$0.05/use
summarize_documentAnalyze and summarize document content with key information$0.10/use
classify_documentClassify document type (invoice, contract, receipt, etc.) with confidence$0.05/use
extract_tablesExtract all tables as structured JSON (headers + rows)$0.10/use

Connect via Claude Desktop

Add to your Claude Desktop MCP settings:

{
"mcpServers":{
"document-intelligence":{
"url":"https://ntriqpro--document-intelligence-mcp.apify.actor/mcp?token=YOUR_APIFY_TOKEN"
}
}
}

Supported Document Types

  • Invoices and receipts
  • Contracts and agreements
  • Business letters and memos
  • Reports and presentations
  • Forms and applications
  • ID documents and certificates
  • Tables, spreadsheets, and charts

Supported Languages

Responses can be generated in: English, Korean, Japanese, Chinese, Spanish.

Input

Each tool accepts:

  • imageUrl (required): URL of the document image
  • language (optional): Response language code (default: "en")

Output

Each tool returns structured JSON with the analysis results.

Example: extract_text

Input:

{
"imageUrl":"https://example.com/invoice.png"
}

Output:

{
"status":"success",
"text":"# Invoice\n\n**Invoice #**: 2024-001\n**Date**: March 15, 2024\n...",
"model":"qwen2.5-vl",
"imageUrl":"https://example.com/invoice.png"
}

Example: classify_document

Output:

{
"status":"success",
"classification":{
"document_type":"invoice",
"confidence":0.95,
"language":"en",
"key_fields":["invoice_number","date","total_amount","vendor"]
}
}

Example: extract_tables

Output:

{
"status":"success",
"tables":{
"tables":[
{
"headers":["Item","Quantity","Price"],
"rows":[
["Widget A","10","$5.00"],
["Widget B","5","$12.00"]
]
}
]
}
}

Technology

  • Vision Model: Qwen2.5-VL (Apache 2.0 License)
  • Processing: Local AI inference, zero external API calls
  • Privacy: Document images are processed in real-time and not stored

Open Source Licenses

This service uses the following open source models:

Platform usage is free. You only pay per event (see pricing above).


๐Ÿ”— Related Actors by ntriqpro

Extend this actor with the ntriqpro intelligence network:

โญ Love it? Leave a Review

Your rating helps professionals discover this actor. Rate it here.

You might also like

Document Extractor API - AI-Powered PDF & Text Analysis

fresh_cliff/document-extractor-api

Extract text and data from PDF, Word, and image documents using AI-powered OCR. Convert documents to structured JSON, analyze content, and extract insights. No API keys required with mirror fallbacks.

๐Ÿ‘ User avatar

Brennan Crawford

2

AI Document Assistant

devninja/ai-document-assistant

This actor analyzes uploaded documents using AI to extract and process information. It helps businesses quickly get answers from their documents and automate decision-making.

Zip Download Extraction Scraper

fresh_cliff/zip-download-extraction-scraper

Download and extract zip files automatically. Extract archives, process documents, analyze logs, backup files. Batch extract text, JSON, CSV content. Real-time data extraction API.

๐Ÿ‘ User avatar

Brennan Crawford

2

Federal Register Documents Scraper

compute-edge/federal-register-scraper

Extract U.S. Federal Register documents via the public API. Filter by query, document types (rules, notices, proposed rules), publication date, and agencies. Includes full document details, citations, and regulatory information.

PDF OCR API - Document Extraction

alizarin_refrigerator-owner/pdf-ocr-api

Extract text from PDFs including scanned documents. OCR processing, table extraction & structured data output. Process invoices, contracts & forms at scale.