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. docs2mcp @docs2mcp/docs2mcpQuery your own PDFs and documents from any MCP client. Every answer cites the page it came from.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  2. PromptReady @hydrojwh/promptready-mcpConvert PDF/CSV to Markdown with AI-powered OCR via the PromptReady cloud API.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  3. pdffr @amersarhan/pdffr-mcpLocal, private PDF to Markdown for agents: geometry-first parsing, OCR only where needed.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  4. Keynote Harvest @hulin42/keynote-harvest-mcpHarvest Keynote and PDF slide decks into previews, text, image assets, and a manifest for agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  5. DiemDesk MCP @diemdesk/mcpConvert Office files and PDFs, OCR a scan, or capture a web page — from your assistant.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  6. Stipple — Document Verification & Extraction @stipple/openwarrantDocument forensics: tamper/AI checks, fields, tables, identity, screening, tenders, citations.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  7. Doc Extract @thestarboy9696/doc-extract-apiSchemaLock — paid extraction: JSON from docs via your schema, x402/USDC.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  8. Doc Extract @koraynar/doc-extract-mcpDocument tooling for AI agents: PDF/text reading, chunking, schema-validated JSON output.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
  9. AgentPay — Pay-per-call AI Microservices @agentpay/agentpay34 pay-per-call AI microservices via x402, USDC on Base, no API keys.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  10. ImagePay MCP @neuralmint/imagepay-mcpImagePay MCP: 40 x402 paid API tools (OCR, PDF, image, QR, tabular, web). Pay per call on Base.19% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  11. Ox402 Utils @hasned-spec/ox402-utils47 micro-priced utilities: search, screenshots, OCR, whois, prices, video downloads. x402 USDC.39% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  12. Deckprobe @deckflow/deckprobeInspect PDF, Office, and iWork documents without rendering: counts, metadata, security signals3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  13. Electronics RFQ Agent @rudrendupaul/electronics-rfq-agentAI quoting agent for electronics distributors. RFQ in, quote out via MCP tools.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  14. Ocr @pennyocr/ocrRead PDFs and images as markdown or text, with exact costs and hard spend caps. $0.75/1k pages.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  15. CPFL: Download + OCR @mcp-dir/contas-cpfl-download-ocr-mcpCPFL: Download + OCR, official-source lookup. Platform-hosted, pay per query with prepaid credit.18% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  16. CPFL: Download via link + OCR @mcp-dir/contas-cpfl-link-ocr-mcpCPFL: Download via link + OCR, official-source lookup. Platform-hosted, pay per query with prepaid c22% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  17. Andreax @moralito311-andr/andreax270 pay-per-call AI tools for agents, paid via x402 (USDC on Base). No signup, no API keys.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  18. MainBook Bank Statement Converter @mainbook/bank-statement-converterConvert PDF bank statements to checked Excel, CSV or JSON with balance validation.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  19. Housecallpro @chrischall/housecallpro-mcpRead Housecall Pro estimates from the customer link your contractor sent you.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  20. Opensolr @opensolr/opensolr-mcpManaged Apache Solr for agents: hybrid BM25+kNN search, server-side embeddings, RAG answers8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  21. ExpenseBot @totesmagotes/mcp-server-authReceipt ingestion, Gmail capture, expense analysis, and reviewed reports for AI-agent workflows.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  22. ocular @xyun1996/ocularVision tools for coding agents: screenshots, OCR, UI diffs, errors, tables, and charts.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  23. Anylens @slowper/anylensTurn videos, PDFs, screenshots, and articles into anchored, cached understanding for agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  24. Construction Takeoff Estimating @esti-maite/construction-takeoff-estimatingConstruction takeoff and estimating for AI agents. Measure a drawing PDF, export a priced estimate.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.