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. Invapi @invapi-org/invapi-mcpExtract, create, convert & validate invoices (UBL, CII, XRechnung, ZUGFeRD, PDF, Excel)4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  2. Iteratools @fredpsantos33/iteratools40+ pay-per-use tools for AI agents: search, TTS, QR, PDF, scraping, image gen. x402.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  3. ESG MCP Servers @freminder/esg-mcp-servers31 MCP tools for ESG data extraction, PDF processing, vector search, and EU regulation analysis.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  4. RAG @fieldcure/ragMCP RAG server with hybrid search, multi-KB support, and AI-powered chunk contextualization.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.
  5. Dokmatiq DocGen @dokmatiq/docgenGenerate PDF, DOCX and Excel documents, e-invoices and signed PDFs, and recognize receipts.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  6. MCP Gemini @crunchtools/geminiMCP server for Google Gemini AI - text, image, video, research, and more4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  7. One MCP, many parsers @adelaidasofia/parse-mcpOne MCP, many parsers. Routes between markitdown, Docling, and LlamaParse. Plus an interpret tool…6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
  8. Document Parser @agenson-horrowitz/document-parserParse and extract structured data from various document formats (PDF, Word, HTML).8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  9. Tollkit @ultrastarz/x402-extractRead pages and PDFs, SEC filings, weather, airport delays, on-chain and x402 data. USDC per call.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  10. Proofetch @vektoris-ai/proofetchVerified extraction: source-backed JSON from PDFs/URLs; honest null + signed receipt.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  11. OTP OJP @testinat0r/otp-ojpValidate, introspect, and parse talent profiles (OTP) and job postings (OJP)3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  12. Boltwork @squidboy30/boltwork-mcpAI services via Bitcoin Lightning — PDF summarisation, code review, translation and more.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  13. Taxformatter @sean-bravo/taxformatterParse crypto CSVs and bank PDFs into clean transaction data for Koinly, TurboTax, CoinLedger.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  14. Pdf4vllm @pyjudge/pdf4vllmPDF reader for vision LLMs. Auto-detects text corruption and switches to image mode.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  15. Suprsonic @o-mega-enterprise/suprsonic-mcpOne API key, dozens of capabilities for your AI agent. Zero provider auth.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  16. Docalyze @lunarperovskite/docalyzeRead and analyze local documents (PDF, Excel, CSV, Word, PowerPoint, images). No API keys needed.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  17. TruePath PDF @joytruepath/truepath-pdf-mcpLocal-only PDF tools for AI — extract text, search, split/merge, render pages. Files never leave.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  18. methods-mcp @flynnlachendro/methods-mcpMCP server for structured methods extraction + reproducibility heuristics on academic papers.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  19. Contract Ops @drbaher/contract-ops-mcpOne MCP server for the contract-ops suite: all nine local-first CLIs as agent tools.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  20. ClicheFactory Document Intelligence @clichefactory/clichefactory-mcpExtract structured JSON from PDFs, images, DOCX, XLSX, CSV, EML attachments, and DSPy pipelines.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  21. Pdf Document @csoai-org/pdf-document-mcpPdf Document MCP Server by MEOK AI Labs10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  22. Ocrspace @pipeworx-io/ocrspaceOCR.space MCP — wraps the OCR.space API (ocr.space) for image/PDF → text OCR.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  23. PDF Tables @mehtaphysical13/pdf-tables-mcpReliable PDF table extraction. Pass a URL, get structured JSON tables with citations.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
  24. Jp M2m Gateway @kodandy/jp-m2m-gatewayRaw Japanese regulatory data for AI agents: pension, gazette, gBizINFO. x402-metered (USDC).6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.