Skip to content

Developer Platform

Document intelligence your code — and your agents — can call.

Build with the most precise document-automation platform. API-first, agent-ready, and engineered for high-scale enterprise workflows.

API-first Architecture

Full REST API, token-based authentication, and OpenAPI 3.0 specifications for seamless integration.

View API Reference
POST /v1/extractions/async
curl -X POST https://api.docupow.com/v1/extractions/async \
  -H "Authorization: Bearer dp_live_xxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "document_url": "s3://enterprise-bucket/invoices/inv-492.pdf",
    "schema_id": "sch_invoice_standard_v2",
    "webhook_url": "https://api.yourcorp.com/webhooks/docupow",
    "options": {
      "confidence_threshold": 0.95,
      "page_range": "1-5"
    }
  }'

The MCP Server for Documents

DocuPOW publishes an MCP (Model Context Protocol) server, so MCP-compatible AI assistants can call DocuPOW's document intelligence directly — search, extract, and verify documents autonomously. Claude can connect from claude.ai today; because MCP is an open protocol, other MCP-compatible clients connect the same way.

Explore MCP Guide
MCP Tool Call Definition
{
  "tool": "extract_document_data",
  "description": "Extracts structured data from a given document reference.",
  "parameters": {
    "type": "object",
    "properties": {
      "document_id": {
        "type": "string",
        "description": "The unique identifier of the uploaded document."
      },
      "target_fields": {
        "type": "array",
        "items": { "type": "string" },
        "description": "Specific fields to extract."
      }
    },
    "required": ["document_id"]
  }
}

Omnichannel Ingestion

Ingest from anywhere your business works.

API

Direct programmatic upload

Email

Managed intake mailboxes

Browser

Web-based uploader and SDK

Mobile

Native iOS/Android capture SDK