scantobill-mcp-server
This server integrates ScanToBill's AI-powered OCR with MCP-compatible AI clients (e.g., Claude Desktop) to extract structured JSON data from business documents and manage extraction history.
Extract structured data (
extract_document): Submit a public URL (PDF, JPEG, PNG, TIFF, WebP) to extract fields like vendor, customer, line items, totals, VAT, and currency from invoices, receipts, contracts, IDs, and other documents. Specify document type (auto, inventory, general, pos, contract, ID) and language (Arabic, English, French, Spanish, or auto). Each extraction consumes one quota unit.List past extractions (
list_extractions): Retrieve history sorted newest first, filterable by date range, document type, status, and limit (up to 100).Fetch specific extraction (
get_extraction): Retrieve full metadata (provider, status, timestamp) by ID.Easy authentication via CLI flag or environment variable, with a free tier available.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@scantobill-mcp-server Extract the invoice data from this URL: https://example.com/invoice.pdf"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ScanToBill MCP Server
What is this?
ScanToBill is an AI-powered OCR platform for Arabic and English business documents — invoices, receipts, contracts, and IDs. This package connects ScanToBill to Claude Desktop (or any MCP-compatible AI client) so you can extract invoice data just by sharing a URL with Claude.
You: "Extract the line items from this invoice: https://example.com/invoice.pdf"
Claude: Here's what I found:
- Consulting services: SAR 5,000
- VAT (15%): SAR 750
- Total: SAR 5,750
Vendor: Al-Noor Trading Co.
Date: 2026-07-15
Invoice #: INV-2026-0042Related MCP server: Mistral OCR MCP Server
Quick start
npx @scantobill/mcp-server --api-key ocr_sk_YOUR_KEYGet a free API key at app.scantobill.com/keys — 20 extractions/month, no credit card.
Claude Desktop setup
1. Open the config file
OS | Path |
macOS |
|
Windows |
|
2. Add this entry
{
"mcpServers": {
"scantobill": {
"command": "npx",
"args": ["-y", "@scantobill/mcp-server", "--api-key", "ocr_sk_YOUR_KEY"]
}
}
}3. Restart Claude Desktop — done.
Available tools
Tool | Description |
| Extract structured JSON from an invoice, receipt, or business document at a public URL |
| List past extractions with optional date, type, and status filters |
| Fetch full metadata for a specific extraction by ID |
extract_document
url (required) Public URL — PDF, JPG, PNG, or TIFF
document_type invoice · receipt · contract · id (default: invoice)
language ar · en · auto (default: auto)list_extractions
limit Number of results (default: 10, max: 50)
status pending · processing · done · failed
from ISO 8601 start date
to ISO 8601 end dateget_extraction
id (required) Extraction ID returned by extract_documentAuthentication
# CLI flag
npx @scantobill/mcp-server --api-key ocr_sk_YOUR_KEY
# Environment variable
SCANTOBILL_API_KEY=ocr_sk_YOUR_KEY npx @scantobill/mcp-serverSupported documents
Type | Arabic | English | Mixed |
Invoice (فاتورة) | ✅ | ✅ | ✅ |
Receipt (إيصال) | ✅ | ✅ | ✅ |
Contract (عقد) | ✅ | ✅ | ✅ |
National ID | ✅ | ✅ | — |
VAT invoice (ZATCA) | ✅ | — | — |
Pricing
Plan | Extractions/month | Price |
Free | 20 | $0 |
Starter | 500 | $15 |
Pro | 5,000 | $49 |
Enterprise | Unlimited | Custom |
License
MIT © ScanToBill
Available Tools
3 toolsextract_documentA
Extract structured data from an invoice, receipt, commercial register, VAT certificate, or other business document at a public URL. Returns JSON with all detected fields including vendor, customer, line items, totals, VAT, and currency. Each extraction consumes one unit from the authenticated user's plan quota.
Inputs: document_url (required), language, document_type.
get_extractionA
Get the metadata for a specific past extraction by its log ID. Returns the document type, OCR provider used, status, and timestamp.
Inputs: extraction_id (required).
list_extractionsA
List past extraction log entries for the authenticated user. Returns extraction metadata (ID, type, provider, date, status) sorted newest first. Use get_extraction for the full details of a specific entry.
Inputs: limit, to_date, from_date, document_type.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: extracting a new document, listing past extractions, and fetching a specific extraction's metadata. No overlap or ambiguity exists.
All tool names follow the same verb_noun pattern with lowercase and underscores: get_extraction, extract_document, list_extractions. Consistent and predictable.
Three tools is slightly minimal but appropriate for a focused extraction service. Each tool serves a distinct need in the extraction workflow, though additional operations like delete or re-extract could be added.
The set covers the core lifecycle: create (extract_document), list (list_extractions), and get (get_extraction). Missing update/delete operations, but extractions are likely immutable, so this is acceptable. A tool to check quota would be a minor addition.
Maintenance
Related MCP Connectors
MCP server unifying ERPs, CRMs, APIs and knowledge base for Claude, ChatGPT and Gemini.
Hosted MCP server: convert PDFs to clean, LLM-ready Markdown with tables, formulas and OCR.
Hosted Amazon Seller and Vendor MCP server for Claude, ChatGPT, Cursor, Codex, Gemini, Copilot.
Document conversion MCP server: PDF to Markdown, image OCR, spreadsheet parsing.
Related MCP Servers
- FlicenseNot gradedqualityNot gradedmaintenanceA Python MCP server for invoice and receipt processing that uses OCR technology to extract data from PDFs and images, offering AI assistants the ability to process, extract text from, and merge invoice documents.2-
- FlicenseNot gradedqualityDmaintenanceAn MCP server that enables Claude to perform OCR on local files using Mistral AI's document processing capabilities. It converts documents and images into markdown format for seamless analysis and interaction.-
- FlicenseNot gradedqualityDmaintenanceAn AI-powered MCP server that extracts structured data from Indian identity documents (Aadhaar, Passport, PAN, Driving License) using OCR, enabling Claude Desktop to read and process document images locally.-
- AlicenseNot gradedqualityDmaintenanceMCP server for ReceiptConverter that allows AI assistants to parse any receipt or invoice image/PDF into structured JSON with a single tool call.MIT