Document data extraction MCP servers

A server here extracts text or fields from documents, receipts or scans (OCR).

Not here: converting file formats.

576servers
295 remote281 localTagged by Odel's AI, which can make mistakes

Best fit

342 made for this, ranked by starsRemoteLocal
  1. FINLY Balance Report Analysis @finly/report-analysisIsraeli mortgage reports with Hebrew results, 15-minute recovery and authorized external OCR.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  2. PDF Text, Table and OCR Extractor @brenton-keller/pdf-text-table-ocr-extractorPDF URLs to per-page text, tables as rows, Markdown, metadata and OCR for scanned pages.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  3. PreteWorks API @preteworks/preteworks-apiOne key for the document-to-web pipeline: scrape, AI-extract, build & edit PDFs, fill forms.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  4. Ardaro Purchase Document Review @ashevilleislove/ardaro-receipt-intelligenceReceipt extraction, invoice-to-PO quantity allocation, and free three-document discrepancy checks.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  5. Statement to Budget @statementtobudget/bank-statement-converterTurn bank statement PDFs, CSVs, XLSX and OFX into categorised transactions plus a summary.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  6. EditalMD @editalmd/editalmdBrazilian public procurement (PNCP): search, deadlines, tender markdown, alerts and watches.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  7. PDFIntact @pdfintact/pdfintactExtract tables, text and formulas from PDFs, including scanned pages and broken text layers.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  8. Invoice & Receipt OCR Extractor to Excel @ranovam/invoice-to-excelInvoice and receipt extractor: reads PDF and image invoices/receipts with AI, pulling date…11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  9. Brainiall Documents @brainiall/documentsHigh-fidelity PDF to structured Markdown conversion and document field extraction.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  10. Brainiall Image @brainiall/imageBackground removal, upscaling, face restore, document OCR, table extraction, visual understanding.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  11. Datanem @datanem/datanemTurn PDFs, scans and photos into a queryable database. Invoices, CVs, receipts, in bulk.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  12. Execute chinese-scroll-digitizer-mcp @evozim/chinese-scroll-digitizer-mcpPremium agentic endpoint for chinese-scroll-digitizer-mcp.19% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  13. Execute b2b-legal-contract-parser-mcp @evozim/b2b-legal-contract-parser-mcpPremium agentic endpoint for b2b-legal-contract-parser-mcp.17% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  14. FactScan AI @factscanai/factscanOCR and document understanding: extract text from images, then summarize or translate it.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  15. Professor Sausages — Web & Documents @professorsausages/sausage-webRead pages & files to text, news, weather, market holidays and timezones via x402.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  16. SMB RFP Copilot @checkmycontractorquote/smb-rfp-copilotExtract RFP requirements, deadlines, compliance items, and response checklist.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  17. Docforge @steviepinero/docforge12 paid document tools: PDF to markdown, OCR, tables, invoices, Word/Excel/HTML, merge/split. x4024% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  18. Space OCR @hwang-yh-cto/space-ocrVerified OCR with per-value coordinates, plus a workspace agents can file documents into and query.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  19. Dropcoin Invoice @freshfos/dropcoin-invoiceGerman e-invoicing: generate XRechnung 3.0, pre-check and extract (incl. ZUGFeRD PDF). Paid.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  20. DataSnipe MCP @datasnipe/datasnipe-mcpExtract structured data points from research papers and other documents with an LLM.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  21. StructForge @askqa/structforgeTurn messy text into strict JSON schemas agents can trust (invoice, receipt, contact, resume).4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  22. FinStat @finstat/finstatDocuments in, reconciled double-entry books out. Statements, invoices, receipts, matched and posted.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  23. PDFHaul MCP @pdfhaul/mcpPDF tools: merge, split, compress, convert, OCR & more. OAuth with auto-registration or API key.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  24. Fci @fluxink/fci-mcpConvert handwriting into text, LaTeX math, chemistry, or molecular structures.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.