DocumentpPro

Extract structured, schema-typed data from invoices, purchase orders, receipts, and tax forms, and classify documents into custom label sets — via a hosted…

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Extract Document: Submit a document for structured data extraction. Asynchronous: returns a request_id immediately — poll check_extraction_status until request_status is completed, then read the extra
  • Check Extraction Status: Check an extraction job. request_status is one of pending, processing, completed, failed, exception. When completed, results.data holds the extracted fields keyed exactly as i
  • Get Credit Balance: Check remaining credits before starting a batch job. Extraction and classification calls fail with INSUFFICIENT_CREDITS once total_credits_remaining reaches zero.

What data it sees

Do you need an account

No: the server works without sign-in

Extract structured, schema-typed data from invoices, purchase orders, receipts, and tax forms, and classify documents into custom label sets — via a hosted MCP server. Free tier included.

How to connect

How to connect DocumentpPro to Claude

The server address to paste into Claude settings:

https://documentpro--adrian-71i6.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect DocumentpPro to ChatGPT

The server address to paste into ChatGPT settings:

https://documentpro--adrian-71i6.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect DocumentpPro to Cursor

The server address to paste into Cursor settings:

https://documentpro--adrian-71i6.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (11)

Raw names from tools/list. Only developers need these.

extract_documentSubmit a document for structured data extraction. Asynchronous: returns a request_id immediately — poll check_extraction_status until request_status is completed, then read the extracted fields from results.data.
check_extraction_statusCheck an extraction job. request_status is one of pending, processing, completed, failed, exception. When completed, results.data holds the extracted fields keyed exactly as in the template schema from get_schema.
get_credit_balanceCheck remaining credits before starting a batch job. Extraction and classification calls fail with INSUFFICIENT_CREDITS once total_credits_remaining reaches zero.
list_templatesList the extraction templates available on this account (invoice, purchase order, tax forms, custom layouts, ...). Use get_schema on a template_id to see the fields it extracts.
get_schemaGet a template's field definitions (name, type, description, nested table columns). Use this to generate a matching data model in your app instead of guessing field names — extraction results in results.data use exactly these names.
create_templateCreate a new extraction template. template_schema example: {"fields": [ {"name": "invoice_number", "type": "text", "description": "The invoice number"}, {"name": "line_items", "type": "table", "subFields": [ {"name": "description", "type": "text"}, {"name": "amount", "type": "number"}]}]} Rules: field names use lowercase letters, digits, underscores and spaces (max 50 chars, unique across the template). Types: text, number, date, radio, checkbox, boolean, object, table. "table" and "object" fields must define "subFields" (inside an object only text, number, boolean, date, table are allowed — no nested objects). Never mark fields required — every field must allow null. Optional per field: "description" (max 500 chars, improves accuracy), "enum" (list of strings, for radio/checkbox). Call get_schema on an existing template for a worked example.
update_templateUpdate a template's title and/or field schema. template_schema replaces the existing schema entirely, so start from get_schema output when adding or changing fields. At least one of template_schema / template_title is required.
classify_documentAssign one of your labels to a document — use it to route mixed document streams to the right extraction template. Pass labels inline for one-off classification, or create_classifier once and reuse it by classifier_id. Provide the document as exactly one of document_id / file_url / file_base64. Classification is synchronous, but a document uploaded for the first time must be OCR'd first — on DOCUMENT_NOT_READY, retry with the returned document_id after ~15 seconds.
create_classifierSave a reusable classifier. Use its classifier_id with classify_document to route documents consistently instead of repeating inline labels.
list_classifiersList the saved classifiers on this account, including their labels — use a classifier_id with classify_document.
list_supported_formatsList the file formats extract_document and classify_document accept.