Document understanding

Everything here was classified as document understanding by keyword match against the maintainer's own description, so treat the grouping as a starting point rather than a verdict.

The list is ordered by the most recent commit, not by stars. A popular project that stopped in 2024 is not a better answer than a smaller one shipped last week.

Listed, not yet verified by us (60)

Published to the registry, but we have not yet checked its repository. Treat the entry as the maintainer’s claim only.

• Sui Knowledge Base (kapa.ai) — v1.0.0
  Semantic search across Sui documentation and knowledge sources, powered by kapa.ai
• MCP Doctor — v0.1.0
  Check and improve the contract quality of any MCP server — for humans, agents, and platforms.
• PasteMD — v1.0.0
  Instant markdown sharing. Create, manage, and share documents with password protection.
• RenderMark — v0.1.10
  Markdown to styled HTML, PDF, DOCX, and slides with themes, diagrams, and math.
• io.github.JonathanWeerakkody/vectorise — v0.2.0
  Vectorize images to SVG and export to PDF, EPS, DXF, PNG, JPG, or WEBP via Vectorise.Me.
• TruePath Office — v0.1.0
  Local MCP for Word, Excel, PowerPoint & PDF on macOS — formulas, slides, DOCX, PDF ops. No network.
• TruePath PDF — v0.3.0
  Local-only PDF tools for AI — extract text, search, split/merge, render pages. Files never leave.
• JSON Contracts — v0.1.2
  JSON contract registry and validator for structured LLM and agent outputs.
• MiOffice — AI-Powered Workspace Studio — v1.0.0
  125+ browser tools for PDF, Image, Video, Audio, AI, Scanner. Files never leave your device.
• io.github.jztan/pdf-mcp — v2.0.0
  Production-ready MCP server for PDF processing with intelligent caching.
• io.github.jztan/qt4-doc-mcp-server — v0.7.0
  Offline MCP server for local Qt 4.8, Qt 5, and Qt 6 documentation with full-text search.
• PubSec Radar — v0.1.0
  Federal sales intelligence: expiring-contract triggers, agency spend intel, deal qualification.
• io.github.Kapeli/dash-mcp-server — v1.1.1
  MCP server for Dash, the macOS API documentation browser. Search 200+ docsets.
• MCP Search Server — v0.1.1
  Web search, content extraction, PDF parsing, plus datetime and geolocation tools. No API keys.
• io.github.kiki830621/che-word-mcp — v1.17.0
  Swift-native MCP server for Word (.docx) manipulation with 148 tools
• VoiceLogPro — v1.0.0
  Voice-to-PDF daily construction reports. Court-ready documentation for subcontractors
• io.github.kitewright/mcp — v0.1.1
  Lightweight browser automation for AI agents: navigate, screenshot, extract, PDF. One small binary.
• io.github.klever-io/mcp-klever-vm — v1.3.0
  MCP server for Klever blockchain smart contract development.
• io.github.klevercv/mcp-server — v1.0.0
  Generate tailored resumes via AI agents using KlevrCV. Returns a signed PDF download URL.
• io.github.kmalakoff/mcp-pdf — v1.0.3
  MCP server for PDF generation using PDFKit
• io.github.korovin-aa97/talkthrough-mcp — v0.2.5
  Local MCP server: screen recordings into transcript, exact frames, OCR, wall-clock evidence.
• io.github.kota1026/smartguard-mcp — v1.0.0
  SmartGuard MCP Server - AI-powered smart contract security audit tools for Claude Code, Cursor,...
• io.github.kumarprobeops/signforge — v1.2.2
  Send documents for e-signature from AI agents. Upload, sign, and download PDFs.
• Frenchie — v0.5.0
  OCR, transcription, file extraction, and image generation for AI agents via MCP.
• io.github.lakshgk/distill-mcp — v0.1.1
  Convert PDF, DOCX, XLSX, PPTX, HTML, audio to token-efficient Markdown for any MCP client.
• reach — v2.0.3
  Documents agents read and write: share & hand off versioned markdown/HTML docs. No account.
• io.github.lazyants/lexware — v5.0.0
  MCP server for the Lexware Office API — invoices, contacts, articles, and vouchers.
• io.github.lazyants/transkribus — v3.0.0
  MCP server for the Transkribus REST API — collections, documents, HTR/OCR, and models.
• io.github.lazymac2x/api-contract-validator — v1.0.0
  Cloudflare Workers MCP server: api-contract-validator
• Designesy — v1.9.1
  Score any URL against a real design contract — 40 checks, A-F grade, token + motion validation.
• Comitelligence — EU Comitology Register — v1.1.1
  Agent-native search of EU comitology: committees, votes, dossiers, and implementing-act documents.
• io.github.lemmaoracle/mcp — v0.0.17
  Verifiable provenance for AI agents — ZK proofs over confidential documents, no plaintext exposure.
• io.github.lesofi/handinloop-mcp-server — v0.4.0
  Human-in-the-loop document extraction: submit a doc, get validated fields and an audit trail.
• io.github.Libres-coder/parseflow — v1.0.2
  PDF parsing server with text extraction, metadata, search, images, and TOC via MCP
• AKD VaultPDF — v1.0.1
  On-device PDF, resume and CSV tools. Files never leave your machine. Refuses rather than guessing.
• io.github.LightSpeedPlusOne/invovate-mcp-server — v0.1.1
  AI-agent invoice generator: PDF, JSON & UBL in 11 languages via the Invovate API.
• BrainTube — v3.12.3
  Search everything you save: YouTube, articles, podcasts, PDFs, Notion, Obsidian. API key or OAuth.
• MinerU — v1.1.4
  MinerU document parsing API — PDFs, images, DOCX, PPTX with OCR and batch processing.
• io.github.llmops-pro/paywall-mcp — v0.1.2
  Lightning-paywall sidecar: wraps any stdio MCP server, requires paid invoices before tool calls.
• io.github.lmaniraruta/license-verify-mcp — v0.1.3
  Verify US contractor license + surety bond + insurance from official state data. WA live, CA beta.
• LocalSynapse - Local File Search MCP Server — v2.1.0
  Offline AI-powered local file search. BM25 + semantic hybrid search across all documents.
• Syftly — v0.1.0
  Ranks the best AI tool or API per task: transcription, TTS, web search, scraping and OCR.
• io.github.lordbasilaiassistant-sudo/base-security-scanner-mcp — v1.0.3
  MCP server to scan smart contracts on Base for honeypots, rug pulls, and vulnerabilities.
• io.github.lordbasilaiassistant-sudo/contract-scanner — v1.0.2
  Smart contract security scanner — vulnerabilities, risk scores, and calldata decoding
• io.github.lordbasilaiassistant-sudo/thryx-portfolio — v1.0.0
  Read-only MCP server for the THRYX onchain portfolio (14 contracts on Base mainnet).
• io.github.Lucav21/heu-mcp — v0.3.0
  HEU Legal e-signature MCP: manage HEU documents and PDFs, prompt signers, download PDFs.
• io.github.lucavisconti211-debug/heu-mcp — v0.1.2
  HEU Legal e-signature MCP: manage HEU documents and PDFs, prompt signers, download PDFs.
• io.github.Lucid-Systems-LLC/lucid-apple-mcp — v0.3.0
  On-device Apple Intelligence as MCP tools for macOS — OCR, tables, entity detection, generation.
• Osigu RCM — v1.0.0
  Gerencie cobranças, invoices e atendimentos do RCM da Osigu diretamente do seu agente de IA.
• Handiworks — v0.1.1
  MCP tools for AI agents: render URLs to image/PDF, check link health, convert HTML/CSV/JSON.
• BACH FileCommander — v1.7.0
  43 tools for filesystem, process management, sessions, search, OCR, ZIP, and PDF export.
• MTA:SA Documentation MCP Server — v1.0.3
  MCP server for MTA:SA documentation with intelligent search and caching
• io.github.LunarPerovskite/docalyze — v0.2.1
  Read and analyze local documents (PDF, Excel, CSV, Word, PowerPoint, images). No API keys needed.
• EasyAccessPDF — v1.0.0
  PDF accessibility checks (veraPDF PDF/UA-1), auto-fix and Markdown conversion. EU-hosted.
• io.github.m2ai-mcp-servers/mcp-ratchet-clinical-charting — v0.1.0
  MCP server for clinical charting with Claude - document patient visits to EMR
• io.github.Mad-Man-Dan/karbon-mcp-server — v0.2.4
  Unofficial MCP server for Karbon practice management: contacts, work, time, invoices, payments.
• io.github.MAIAS-project/maias — v0.5.1
  Validate, query, safely edit, and wireframe MAIAS app-IA documents: cascading renames, atomic edits.
• io.github.makririch/buchpilot — v0.1.2
  DACH accounting for AI: connect sevDesk & Lexoffice to create invoices, contacts, vouchers.
• io.github.makririch/einvoice — v0.1.3
  XRechnung & ZUGFeRD: create, validate, and convert German e-invoices. EN 16931 compliant.
• Spendlog — v1.0.4
  MCP server for expense tracking, invoices, budgets, and financial insights directly in Claude

Page 10 of 17

• ← Previous
• Page 1
• Page 8
• Page 9
• Page 10 (you are here)
• Page 11
• Page 12
• Page 17
• Next →

How this page is ordered

Entries are grouped by whether anyone is still working on them, using the date of the most recent push to the repository. They are not ordered by stars, because a star is a bookmark somebody left once and never took back.

Where we have not checked an entry yet, it says so rather than being mixed in with the verified ones.