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. Kamai @kamai/mcpAI takeoff for construction: turn PDF blueprints into structured, traceable quantities.Not assessed yet.A remote server; you sign in with your account.
  2. PDF Text Extractor for AI Agents @industrial-platform-ai/pdf-textx402 PDF text, pages, and metadata for AI/RAG. $0.0015 per successful PDF.Not assessed yet.A remote server; no sign-in.
  3. Arkrel @arkrel/arkrelTurn documents into verified, structured data: fields, tables, and automatic checks.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  4. Sheet Music OMR @raulkivi/omr-mcpConverts photos or scans of printed sheet music to MusicXML with optical music recognition3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  5. PaperOffice AI @paperoffice-ai/paperoffice-mcpDocument AI and headless DMS: OCR, IDP, search, workflows, signatures. EU-hosted, OAuth 2.1.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  6. BookingTruth Booking Assurance @bookingtruth/bookingtruthVerifies travel bookings against supplier-authoritative evidence; honest UNKNOWN verdicts.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  7. Stipple — AI Text Detection @stipple/openwarrant-aitextIs this prose AI-written? A probability with the tells behind it. Free to start, no key.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  8. Mindee MCP by usefulapi @usefulapi/mindeeTurn PDFs and images into typed fields — invoices, receipts, IDs and custom models — via Mindee OCR.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  9. OCR Images @walmes1/ocr-imagesOCR local Windows : PDF scannes, photos et captures vers texte, plus allegement d'images5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
  10. Korean Notice (공고) Checklist @rosieoh/korean-notice-mcpCompare Korean public notices (HWP/HWPX): changed eligibility, documents, deadlines, with evidence2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  11. File Processor @intelagentstudios/mcp-file-processorText extraction, keyword extraction, language detection, and chunking for RAG11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  12. Siglata @siglata/mcpSoftware for your AI: company files, spreadsheets and rules, with per-person access and history.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  13. Rock's Apify Utility Actors @maindtim/rock-apify-toolsSeven pay-per-event Apify Actors (PDF/CSV/links/sitemap/email/phone/VAT) as MCP tools.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  14. AIDataParser @shibley/aidataparserPDFs, images and messy text to schema-guaranteed JSON. try_parse runs a real extraction, no key.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  15. Kanto Labs @akhiyugo/kanto-labs-mcpWeb data, SEO, domain, company, trends, OCR, document and image tools for AI assistants via Apify.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
  16. Lupa — local file search for your Mac @paeyoungpark-web/lupa-mcpSearch your Mac's files by name and by text inside documents. Local index, Korean-aware.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  17. tiny-context — efficient file tools by AVRG3 @warddamn/tiny-contextLocal document queries, saved extraction profiles, spreadsheet SQL, logs and keyed JSON changes.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
  18. Markdown Notes @narashiman-k/markdown-notes-mcpConvert PDF, Word, Excel, PowerPoint, EPUB and images to Markdown locally, with no upload.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  19. Prism by Parad1gm: Contract Deadlines and Critical Dates @parad1gm/prismCritical dates and deadlines in leases, loans, policies, HOA docs and contracts, with the clause.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  20. passwerk @shahriarbijoy/passwerkOffline EU Battery Passport compiler: ingest documents, map, validate (IDTA 02035), emit AASX.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  21. Epstein @pipeworx-io/epsteinThe Epstein investigation document corpus — the documents themselves, plus9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  22. Dharmamitra @alex-deus/mcp-dharmamitraDharmamitra OCR for Tibetan / Sanskrit / Devanagari images; writes extracted text to a file.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  23. Quality Control Plan Generator @imnoo/quality-control-planQuality control plans from drawing PDFs: auto-extracted tolerances, balloons, Excel + PDF reports.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  24. Convertisseur IA @walmes1/convertisseur-iaDocuments (PDF, Word, Excel, PowerPoint, CSV) vers Markdown leger pour l'IA, 100 % local5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.