Document data extraction MCP servers

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

Not here: converting file formats.

573servers
292 remote281 localTagged by Odel's AI, which can make mistakes

Best fit

341 made for this, ranked by starsRemoteLocal
  1. PDF Triage @vishalmeena2211/pdf-triage-mcpRead local PDFs without uploading. Classifies first, flags untrustworthy text, bounds output.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  2. RentRollAPI @ekvanauk/rentrollapiExtract verified data from CRE rent rolls and T12 operating statements (PDF, Excel, CSV, scans)3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  3. Arachne @samuelfmedeiros/arachne-mcpArachne MCP — scraping, browser, vision, OCR, RAG, Social Research, GitHub + VRT (56 tools).18% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  4. VibeLawyer @jack-mi/vibelawyerLocal MCP for Chinese criminal dossier review; Word notes + Excel catalogs stay on-device.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  5. Auto-Reader OCR — Arabic-first OCR & translation @auto-reader/ocrArabic-first OCR, translation and document extraction. First call mints a free trial key.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  6. InvoiceOracle @tooloracle/invoiceoracleInvoiceOracle - 10 e-invoicing tools: XRechnung, ZUGFeRD, Peppol, validation, archive.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  7. Blixtworks @blixtworks/tools63 pay-per-call tools for agents: vision, text, data, web, blockchain. USDC on Base via x402.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  8. AKD VaultPDF @lifeabundantly/akd-vaultpdfOn-device PDF, resume and CSV tools. Files never leave your machine. Refuses rather than guessing.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
  9. Aviation Accident Analysis MCP @hzy9981/aviation-accident-analysisAviation accident report parsing and prompt generation service under the SHELL framework.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  10. GroupDocs Parser @groupdocs-parser/groupdocs-parser-mcpMCP server for GroupDocs.Parser — extract text, images, metadata, tables, barcodes via AI.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
  11. GroupDocs Total @groupdocs-total/groupdocs-total-mcpMCP server for GroupDocs.Total — annotate, sign, convert, watermark, parse, redact documents via AI.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
  12. Foundry/API @angelus213/foundry-apiBounded tools for rendering, extraction, RAG, enrichment, local discovery and review analysis.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  13. Denpyo @vladic-corp/denpyo-mcpJapanese invoice/receipt OCR + tax registration-number (T-number) verification, via x402.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  14. Kitbag @syedtaj7/kitbag-mcpZero-config MCP server bundling 50+ utility tools: converters, OCR, scraping, and formatters.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  15. Docs @shreyas-profile/docs-mcpVector RAG store for Word/Excel/PDF/PowerPoint. Break-even pricing, $5 per 5,700 pages.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  16. Techtenstein PDF @sathvic-kollu/techtenstein-pdfPDF text and table extraction plus metadata. Supports OCR for scanned documents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  17. PDF4me @pdf4me/pdf4me-mcpPDF & document automation via the PDF4me API — convert, OCR, extract, edit, secure.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  18. WebberSites x402 @webberdesign/webbersites-x402-mcp45 pay-per-call AI agent tools + wallet-owned agent memory. Scraping, SEO, lint, crypto. x402 USDC13% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  19. Suparse Document Processing @suparse/suparse-mcpExtract structured data from PDFs and documents with Suparse AI OCR.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  20. AILANG Parse @sunholo-data/parseDeterministic DOCX/PPTX/XLSX/PDF parser: track changes, comments, headers, footers, merged cells.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  21. Recite MCP @rivradev/recite-mcpLocal MCP server for Recite receipt processing with ledger and memory tools.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  22. PyMuPDF @penny4nonsense/mcp-pymupdfMCP server for reading PDFs using PyMuPDF. Supports local files and URLs.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  23. ParseRelay @parserelay/mcpParse a document into structured, confidence-scored fields. Bring your own model, pay per scan.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  24. Scholar @mlintangmz2765/scholarHardened Scholar MCP for deep academic research (Scopus, OpenAlex, Unpaywall) with PDF vision.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.