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. HKEx Filings @simonplmak-cloud/hkex-filingsLive HKEx (Hong Kong Stock Exchange) regulatory filings for AI agents.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.16 GitHub stars.
  2. Mistral @swih/mistral-mcpMistral MCP server: extract invoices and documents from text, Markdown or OCR into typed JSON.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.15 GitHub stars.
  3. SharePoint MCP Server @ravikant1918/sharepoint-mcpMCP server for Microsoft SharePoint — manage folders, documents, and metadata.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.12 GitHub stars.
  4. Foxit PDF API MCP Server @foxitsoftware/foxit-pdf-api-mcp-serverMCP server that exposes Foxit PDF API capabilities via stdio.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.12 GitHub stars.
  5. Paxa Labs @paxalabs/mcpThai, English, Mandarin speech AI: TTS with playback, transcription, translation, OCR, extraction4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.10 GitHub stars.
  6. MinerU @linxule/mineruMinerU document parsing API — PDFs, images, DOCX, PPTX with OCR and batch processing.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.10 GitHub stars.
  7. PDF toolkit @aryanbv/pdf-toolkit-mcpWrite-capable PDF toolkit MCP: 22 tools to read, create, render, encrypt, merge & fill PDFs.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.10 GitHub stars.
  8. Document to JSON – PDF Invoice/Statement/Contract Parser @fashionmascherine-svg/document-to-json-mcpTurn any PDF into structured JSON via AI + OCR: invoices, bank statements, contracts.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.8 GitHub stars.
  9. Docsift @anishmoncivarghese/docsiftConvert a document once, then get back only the passages that answer a question.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.7 GitHub stars.
  10. KIAgent @localkiagent/kiagentYour mail, chats and documents indexed into a local SQLite corpus, served to AI clients over MCP.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.7 GitHub stars.
  11. Macos Vision @woladi/macos-vision-mcpLocal OCR & screen understanding for agents: read any window, find what to click. No uploads.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
  12. Markdown @ofershap/markdownMarkdown MCP — search, extract sections, list headings, find code blocks.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.7 GitHub stars.
  13. Florence2 @jkawamoto/mcp-florence2An MCP server for processing images using Florence-24% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.7 GitHub stars.
  14. Expense @assaf/expenseReceipt tracker with no friction: receipts arrive by email and file themselves6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.6 GitHub stars.
  15. oxidize-pdf MCP Server @bzsanti/oxidize-pdf-mcpMCP server for PDF generation, parsing, splitting, merging, and manipulation via oxidize-pdf2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.6 GitHub stars.
  16. Open Legal Chile @elpabloultron/open-legal-chileSuite de Inteligencia Jurídica y 55 herramientas MCP para Chile: BCN, PJUD, doctrina y OCR.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
  17. OmniScholar @luffysolution-svg/omnischolarLiterature, Zotero, PDF, citation, materials, and scientific image tools for research agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
  18. Local Delegate @zahirinatzuke/local-delegateDelegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.5 GitHub stars.
  19. Talonic @talonicdev/talonic-mcpExtract structured, schema-validated data from PDFs, scans, images, spreadsheets, and forms.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.5 GitHub stars.
  20. Oncofiles @peter-fusek/oncofilesAI-powered medical document management for cancer patients. Google Drive, Gmail, Calendar via MCP.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.5 GitHub stars.
  21. Ezpzfile @ezpzfile/ezpzfileLocal file tools for agents: documents, PDFs, images, QR codes. Nothing is uploaded.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
  22. Scholar RAG MCP @notwhiteblank/scholar-rag-mcpAcademic paper knowledge-base MCP server: PDF ingest, vector search with reranking, KB management.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.4 GitHub stars.
  23. eKYC Suite @wefi-ai/ekyc-suiteKYC / eKYC MCP server for face compare, liveness, OCR, and image labeling.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.4 GitHub stars.
  24. Samsung Notes @mhemd139/samsung-notesRead Samsung Notes: typed text, tables, handwritten pages, photos and PDFs. Never changes a note.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.