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. Receipts @theluckystrike/receiptsParse raw receipt lines into itemized totals with tax. All data is local.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
  2. Danish annual reports (CVR) @mikkelmanniche-dk/dk-regnskab-mcpKey figures, history and all tagged facts from Danish companies' annual reports (XBRL).3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  3. Pdf Merge Split Stamp Extract Text @bestremotetools/pdf-merge-split-stamp-extract-textMerge, split, rotate, stamp and read PDFs from chat. Page ranges and watermarks, all on your machine6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
  4. NetCafe Documents @ainetcafe/netcafe-docsStatements, invoices, tables, ledgers — every result carries its own arithmetic proof.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  5. APICK @apick/allAPICK Korean data, simple-auth lookups, OCR, search, conversion, image, video and TTS18% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  6. APICK Identity @apick/identityKorean ID document verification and PII masking APIs12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  7. ParseRail @thecompound/parserail-mcpDocuments to schema-valid JSON plus 38 more finished-job AI tools, on one credit wallet.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  8. BensPDF @benbergner/benspdfRead PDFs locally: text, pages, metadata, scan detection, layout, permissions, render, OCR.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
  9. Mexican Tax & Banking @ortamarco/mx-fiscal-mcp-serverValidate RFC, CURP, CLABE and NSS, read CFDI 4.0 invoices and check their SAT status. No keys.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  10. BookMCP @prem5123/bookmcpCited book knowledge for agents working on system design and implementation.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
  11. Visiongemma @q1023884985/visiongemmaLocal AI vision MCP server for Windows: OCR, chart analysis, scene description. 100% offline.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
  12. Signal Nodus SEC Filings @signalnodus/sec-filingsAmendment-safe 10-K/10-Q section diffs, claim checks vs XBRL, 8-K events. Accuracy published.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
  13. Pdf @wesseltl/pdf-mcpExtract text and tables from PDFs for an agent: invoices, reports, statements.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
  14. Dates-LE @nolindnaidoo/dates-leExtract dates and timestamps from logs, data files and code, with their format and position.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  15. AI NetCafé @ainetcafe/ai-netcafeTables and ledgers checked by arithmetic, not by a model. 24 tools. MCP 2026-07-28 ready.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  16. acikpoz @gulmezeren2-byte/acikpozTurkish public construction unit-price (birim fiyat) catalog PDFs into structured pozes4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
  17. Unstructured Transform @unstructured/transformTurn documents into structured, AI-ready data by parsing, enriching, chunking, and embedding.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
  18. ForceDream @forcedreamai/mcp-serverDiscover, invoke, and trustlessly verify ForceDream AI agents with cryptographic proofs. 17 tools.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  19. md-vision @japlete/md-visionRead markdown with inlined images and index headings for agentic RAG workflows.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  20. FlexOrch @dev-flexorch/flexorch-mcpClassify documents, extract structured fields, mask PII, export JSONL/RAG datasets for AI agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
  21. Legal Doc Analyzer @dbsectrainer/mcp-legal-doc-analyzerDomain-specific MCP tooling for legal document workflows4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  22. Bankstatemently @bankstatemently/bankstatemently-mcpConvert PDF bank statements into structured transactions, accounts, and balances.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
  23. AI HR Management Toolkit @xjtlumedia/ai-hr-management-toolkitAI HR toolkit: 24 MCP tools for resume parsing, skill extraction & ATS management.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
  24. PDF Reader @xvvln/pdf-reader-mcpMCP server for extracting text, images, tables, links, annotations, and metadata from PDF files.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.