ZBS Index What actually exists in applied AI, with the source next to it

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.

Worked on in the last 90 days (60)

Someone pushed a commit recently. This is the shortlist worth trying first.

  • io.github.groupdocs-merger/groupdocs-merger-mcp — last commit 2026-07-25, v26.7.2
    MCP server for GroupDocs.Merger — merge, split, and inspect documents via AI agents.
  • io.github.groupdocs-watermark/groupdocs-watermark-mcp — last commit 2026-07-25, v26.7.2
    MCP server for GroupDocs.Watermark — add and search document watermarks via AI agents.
  • Pagewatch — last commit 2026-07-25, v0.2.3
    Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup.
  • boxpdf — last commit 2026-07-25, v1.0.3
    Resource-only MCP server with docs and templates for the boxpdf TypeScript PDF layout library.
  • boxpdf-html — last commit 2026-07-25, v1.6.0
    Render HTML to PDF (html_to_pdf) plus boxpdf library docs and templates, for AI agents.
  • io.github.ExpertVagabond/sui-mcp-server — last commit 2026-07-25, v0.4.2
    53-tool MCP server for Sui blockchain — wallets, DeFi, Move contracts, staking, SuiNS, analytics
  • io.github.edsonvmendes/miniframe-tools — last commit 2026-07-24, v1.2.0
    Brazilian tools for agents: Pix codes, CEP, CNPJ + web capture and PDF. Pay per call.
  • Documentero — last commit 2026-07-24, v0.1.2
    List Documentero templates, inspect field schemas, and generate Word/PDF/Excel documents.
  • Peil — last commit 2026-07-24, v0.1.3
    Log hours, draft invoices and check where you stand — finance for Dutch freelancers.
  • io.github.GrabzIt/mcp-server — last commit 2026-07-24, v1.0.1
    Official GrabzIt MCP server for AI web scraping, screenshots, and PDF/DOCX generation.
  • Biel.ai — last commit 2026-07-22, v2.0.0
    Query your product docs from AI tools. Source-cited answers from your indexed documentation.
  • io.github.AryanBV/pdf-toolkit-mcp — last commit 2026-07-22, v0.3.1
    Write-capable PDF toolkit MCP: 22 tools to read, create, render, encrypt, merge & fill PDFs.
  • dev.pdfops/pdfops-mcp — last commit 2026-07-22, v0.1.1
    Deterministic PDF tools for AI agents: inspect fields, fill forms, merge PDFs, invoices.
  • Bankruptcy Observer — last commit 2026-07-20, v1.1.0
    US business bankruptcy MCP: filings, dockets, documents, case summaries. Free tier + subscription.
  • InvoiceXML — last commit 2026-07-20, v1.0.0
    Create, validate, convert & extract compliant e-invoices (UBL, Factur-X, ZUGFeRD, XRechnung)
  • com.jamesrosingmd/zenoti — last commit 2026-07-20, v1.0.0
    MCP server for Zenoti spa/wellness/medspa — guests, appointments, bookings, invoices
  • PDF Redaction MCP — last commit 2026-07-20, v1.0.0
    MCP server for detecting and redacting PII (Personally Identifiable Information) in PDF documents.
  • Unreal Engine API Documentation — last commit 2026-07-19, v0.3.0
    Accurate UE5 C++ API docs for AI agents. Prevents hallucinated signatures and includes.
  • Unity API Documentation — last commit 2026-07-19, v2.1.0
    Accurate Unity API docs (2022/2023/6) for AI agents. Prevents hallucinated signatures.
  • Canvora — last commit 2026-07-19, v1.2.0
    Turn any idea, URL, doc, or PDF into on-brand visuals: 100+ formats, native in 150+ languages
  • Token Safety & Contract Risk API — last commit 2026-07-19, v1.1.0
    Token safety check — honeypot, tax, proxy, blacklist, risk score. GoPlus-powered. x402.
  • Screenshot & PDF Capture API — last commit 2026-07-19, v1.2.0
    Capture screenshots (PNG/JPEG/WebP) and generate PDFs from any URL. x402 payments.
  • PDF Generator API — last commit 2026-07-19, v1.1.0
    Generate PDF from HTML or Markdown with custom pages, margins, layout. x402.
  • OCR Text Extraction API — last commit 2026-07-19, v1.1.0
    Extract text from images using OCR. Tesseract-powered. x402 micropayment.
  • io.github.gabrielmahia/fomu-mcp — last commit 2026-07-18, v0.1.4
    MCP server for government forms and document workflows in Kenya (fomu = form)
  • com.billingserv/mcp — last commit 2026-07-18, v0.1.9
    BillingServ MCP server for customers, invoices, orders, packages, licenses, and revenue reports.
  • io.github.Bharath-code/regressguard — last commit 2026-07-18, v0.1.1
    Deterministic API regression checks for AI agents: snapshot a baseline, catch broken contracts.
  • vocce transcribe — last commit 2026-07-18, v1.1.0
    Agent media tools: transcribe, summarize, notes, flashcards, doc Q&A, PDF compress. No API key.
  • io.github.csacanam/voulti — last commit 2026-07-17, v0.1.0
    Accept crypto payments from AI agents: invoices + hosted checkout on 5 chains. No API key.
  • app.superdocs/superdocs — last commit 2026-07-17, v1.2.0
    AI document editing for agents: draft, edit, export .docx/PDF. 37 MCP tools; agent self-signup.
  • PuzzleTide — last commit 2026-07-17, v0.2.1
    Word search, crossword, and sudoku generators, printable PDF worksheets, and verifiable LLM evals.
  • com.hushvert/mcp — last commit 2026-07-16, v0.1.0
    File conversion for AI agents: office docs, PDF to Word, video, and LLM-ready markdown via API.
  • Government Contracts MCP — last commit 2026-07-16, v1.0.0
    Government contract search and federal procurement data: SAM.gov opportunities + USASpending awards.
  • io.github.DrBaher/contract-ops-mcp — last commit 2026-07-16, v0.3.0
    One MCP server for the contract-ops suite: all nine local-first CLIs as agent tools.
  • io.github.codespar/mcp-bling — last commit 2026-07-16, v0.2.2
    MCP server for Bling — ERP: products, orders, invoices (NF-e/NFS-e), stock, AR/AP, webhooks
  • io.github.codespar/mcp-caf — last commit 2026-07-16, v0.1.2
    MCP server for Caf — Brazilian KYC/KYB: face auth + liveness, document OCR, orchestrated onboarding
  • io.github.codespar/mcp-certta — last commit 2026-07-16, v0.1.2
    MCP server for Certta — Brazilian KYC/KYB: biometrics, OCR, ICP-Brasil e-signature, onboarding
  • io.github.codespar/mcp-iugu — last commit 2026-07-16, v0.2.2
    MCP server for iugu — invoices, subscriptions, customers, payment methods
  • io.github.codespar/mcp-jumio — last commit 2026-07-16, v0.2.2
    MCP server for Jumio — global identity verification + KYX: documents, liveness, AML screening
  • io.github.codespar/mcp-omie — last commit 2026-07-16, v0.2.2
    MCP server for Omie — ERP, customers, products, orders, invoices, financials
  • io.github.codespar/mcp-onfido — last commit 2026-07-16, v0.2.2
    MCP server for Onfido — global identity verification + KYC: applicants, documents, checks, workflows
  • io.github.codespar/mcp-quickbooks — last commit 2026-07-16, v0.2.2
    MCP server for QuickBooks Online (Intuit) — customers, invoices, payments, items, accounts, P&L
  • io.github.codespar/mcp-stark-bank — last commit 2026-07-16, v0.2.2
    MCP server for Stark Bank — transfers, boletos, invoices, Pix, balance
  • io.github.codespar/mcp-stripe-acp — last commit 2026-07-16, v0.1.4
    Stripe ACP — AI agent checkout, payment delegation, products, invoices
  • io.github.codespar/mcp-tiny — last commit 2026-07-16, v0.2.2
    MCP server for Tiny ERP — products, stock, warehouses, price lists, orders, invoices, AP/AR
  • io.github.codespar/mcp-unico — last commit 2026-07-16, v0.2.0-alpha.3
    MCP server for Unico — Brazilian identity + KYC: CPF/CNPJ, OCR, face match, liveness, PEP/watchlists
  • io.github.codespar/mcp-vindi — last commit 2026-07-16, v0.2.2
    MCP server for Vindi — recurring billing, subscriptions, invoices
  • io.github.codespar/mcp-xero — last commit 2026-07-16, v0.2.2
    MCP server for Xero — global cloud accounting: contacts, invoices, payments, items, reports
  • Facture Électronique France — last commit 2026-07-15, v0.8.0
    MCP server for French e-invoicing (XP Z12-013). Manages invoices, validation and compliance.
  • io.github.andrea9293/mcp-documentation-server — last commit 2026-07-15, v1.15.2
    Local-first document management and semantic search for AI coding agents
  • io.github.amer-prog/gamma-mcp-server — last commit 2026-07-15, v1.0.0
    Create presentations, documents, and webpages from any MCP-compatible AI assistant via Gamma.app
  • ConvergeQA Reviews (Critique & Iterate) — last commit 2026-07-12, v0.2.0
    Multi-model Critique and Iterate document reviews with public verification receipts.
  • Ainecto — last commit 2026-07-12, v0.1.2
    Ainecto MCP connector for workspace, document, ERD, diagram, task, and attachment workflows.
  • ai.callmcp/server — last commit 2026-07-11, v0.1.2
    One MCP tool contract for telephony — any call provider, hosted, local, or BYOK.
  • AgentBodega MCP — last commit 2026-07-09, v0.1.7
    Discover AgentBodega paid data tools, contracts, and x402/L402 HTTP payment handoff metadata.
  • io.github.cx-anand-nandeshwar/dlp-mcp — last commit 2026-07-08, v1.0.0
    The DLP MCP provides the compliance violation in the one drive, google drive documents.
  • doc2mcp — last commit 2026-07-08, v1.0.1783805784
    MCP server for doc2mcp documentation, generated by doc2mcp.
  • freefirecommunity — last commit 2026-07-08, v1.0.1785564364
    MCP server for freefirecommunity documentation, generated by doc2mcp.
  • network — last commit 2026-07-08, v1.0.1785624232
    MCP server for network documentation, generated by doc2mcp.
  • skill — last commit 2026-07-08, v1.0.1785400102
    MCP server for skill documentation, generated by doc2mcp.

Page 3 of 17

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.