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. Bulk OCR: Image & Scanned PDF to Text from CSV or Google Sheet @nero-engine/bulk-ocr-image-pdf-to-textOCR every image and scanned PDF linked in an Apify dataset, CSV, Excel or Google Sheet, keeping...8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  2. Portravo Construction Takeoff @portravo/construction-takeoffReview construction plan takeoffs and download reviewed estimates with Portravo account linking.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  3. Dokyumi Document Extraction @dokyumi/document-extractionExtract attached documents with saved schemas and review owned results, confidence and validation.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  4. Conversion Tools @conversiontools/mcpConvert files too big or exotic for a sandbox: 140+ formats, batch, OCR, AI extraction, TTS/STT9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  5. Document Intel @sercanmetalore/document-intel-mcpBelge Zekası MCP sunucusu — TR fatura/fiş OCR→JSON çıkarımı (kural tabanlı, anahtarsız; opsiyonel…9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  6. Razi Document Tools @razikallayi/razi-documentsDocument processing over MCP: merge, split and compress PDFs, run OCR, extract document text.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  7. Razi Tools @razikallayi/razi-toolsPDF, image, video, OCR, screenshot, SQL, QR and text tools for agents. No API key, no signup.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  8. SchemaSure — structured extraction @noamjose/schemasureExtract schema-valid JSON from text/HTML or document images. Pay per call via x402 V2.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  9. Medigami @maximusrufus/medigamiAttested healthcare-finance MCP: bill scans, appeals, denials, rate + ICD/CPT/NPI lookups.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  10. PolDex @lordolami/poldexMCP server exposing PolDex commercial insurance extraction tools to AI agents.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  11. Handinloop @lesofi/handinloop-mcp-serverHuman-in-the-loop document extraction: submit a doc, get validated fields and an audit trail.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  12. DicePDF @ishan-maheshwari/dicepdfLocal-first PDF tools for AI agents: merge, split, extract, render, compress. Files stay on-device.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  13. Jp Doc Intel @infoinlet-marketplace/mcp-jp-doc-intelJapanese document AI for agents — invoice/meishi extraction, OCR, classification (hosted API).5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  14. Perception @egorthinks/perceptionPerception for AI agents: media QC asserts, image diff, OCR tiles, video/audio analysis, PDF, 3D.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  15. Parsel @ahutto87/parselParse logistics PDFs (Bills of Lading, customs declarations, invoices) into DCSA JSON.19% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  16. RQ SCAN @recerqa/rq-scanMCP Server for RQ-SCAN - AI-powered document OCR and data extraction platform9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  17. Docweave — PDF generation & reading @nicolasmartalog/docweave-mcpGenerate and read PDFs for AI agents: a generate_pdf and a read_pdf tool, priced per document.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  18. Toolora MCP Server @mistakili/toolora-mcp12 free tools: PDF, OCR, QR codes, audio transcription, URL scraping, Excel, Word. No key needed.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  19. Lucid Apple @lucid-systems-llc/lucid-apple-mcpOn-device Apple Intelligence as MCP tools for macOS — OCR, tables, entity detection, generation.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  20. MCP Search Server @kazkozdev/searchWeb search, content extraction, PDF parsing, plus datetime and geolocation tools. No API keys.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  21. Rosetta PDF @jcjimenezglez/rosetta-mcpParse, extract, split, and ask over digital PDFs (text layer, no OCR) from Cursor and Claude.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  22. Invoice Preflight @ahmet11159/invoice-preflightEvidence-backed UBL, PDF, and image invoice checks before approval or payment.18% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  23. doc-convert-mcp @ioconnex/doc-convert-mcpDocument conversion and OCR for AI agents: PDF, Office docs, images to text.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  24. Iteration Layer @iterationlayer/mcpComposable APIs for document extraction, image transformation, and document & sheet generation.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.