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 (50)

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

io.github.degenlegion-com/waxseal — last commit 2026-07-07, v1.0.2
Ed25519 identity for AI agents. Verify seals, sign documents, gate actions with approvals.
Claude KVM — last commit 2026-07-06, v2.0.12
MCP server — control remote desktops via VNC with a native Swift daemon and Apple Vision OCR
ai.smithery/ref-tools-ref-tools-mcp — last commit 2026-06-26, v3.0.0
Provide your AI coding tools with token-efficient access to up-to-date technical documentation for…
Dokmatiq DocGen — last commit 2026-06-26, v0.1.2
PDF/DOCX/Excel generation with stationery overlay, ZUGFeRD/XRechnung, signing, receipt OCR.
io.github.CSOAI-ORG/pdf-merge-ai-mcp — last commit 2026-06-26, v1.0.4
pdf-merge-ai-mcp MCP server by MEOK AI Labs
io.github.CSOAI-ORG/pdf-document-mcp — last commit 2026-06-26, v1.0.4
pdf-document-mcp MCP server by MEOK AI Labs
io.github.CSOAI-ORG/chas-elite-prep-mcp — last commit 2026-06-26, v1.0.11
CHAS / SafeContractor / Constructionline pre-qualification preparation. Health & safety, environ...
Document to JSON – PDF Invoice/Statement/Contract Parser — last commit 2026-06-25, v1.0.0
Turn any PDF into structured JSON via AI + OCR: invoices, bank statements, contracts.
File AI — last commit 2026-06-24, v0.1.1
Agent-ready local document context with stable anchors.
PDFMakerAPI — last commit 2026-06-24, v1.0.0
Turn a description into a shareable, editable PDF — invoices, certificates, reports, resumes.
io.github.gustavoatar/remodeleriq — last commit 2026-06-22, v1.0.0
Check if a contractor's remodeling bid is fair: analyze a quote, get cost + labor estimates.
Giskard Search — last commit 2026-06-22, v0.1.1
Pay-per-use web search for AI agents. Lightning invoice, Ed25519 signature, karma discounts.
Billium — last commit 2026-06-22, v0.1.3
Official Billium MCP server: manage crypto invoices, payments, and webhooks from any MCP host.
EZ@Work — last commit 2026-06-19, v0.1.0
Manage clients, projects, time, and invoices in EZ@Work — business management for freelancers.
GuruPDF — last commit 2026-06-19, v0.1.4
Convert, compress & merge PDFs and 100+ file formats from any AI agent. By GuruPDF.
LayerOne (DocX + Sign) — last commit 2026-06-18, v1.0.0
MCP server for LayerOne DocX (documents & Factur-X) and Sign (e-signature) APIs.
ClicheFactory Document Intelligence — last commit 2026-06-17, v0.1.8
Extract structured JSON from PDFs, images, DOCX, XLSX, CSV, EML attachments, and DSPy pipelines.
Word AI — last commit 2026-06-17, v0.8.6
Structure-preserving Word DOCX editing MCP server and Office.js bridge for AI agents.
io.github.FormatixAI/mcp-server — last commit 2026-06-16, v0.1.1
Branded talent docs: assessment reports, profiles, shortlists & proposals in DOCX/PPTX/PDF/Excel
ai.presentations/presentations-ai — last commit 2026-06-16, v1.0.0
Presentations.AI MCP server — create designed slide decks from a topic, text, or document.
Lovie Company Formation — last commit 2026-06-16, v1.0.10
Form companies, manage bank accounts, cards, invoices and more — directly from your AI coding tools.
io.github.Aimino-Tech/office-oxide-mcp — last commit 2026-06-16, v0.2.1
Rust-native MCP server for Office document processing
io.github.CSOAI-ORG/meok-tacho-audit-mcp — last commit 2026-06-16, v1.0.3
UK haulage tachograph audit + drivers' hours + DVSA OCRS Red prevention. Smart Tachograph 2 (July
io.github.CSOAI-ORG/legal-document-ai-mcp — last commit 2026-06-15, v1.0.4
legal-document-ai-mcp MCP server by MEOK AI Labs
io.github.CSOAI-ORG/invoice-generator-ai-mcp — last commit 2026-06-15, v1.0.4
invoice-generator-ai-mcp MCP server by MEOK AI Labs
io.github.CSOAI-ORG/document-comparison-ai-mcp — last commit 2026-06-15, v1.0.4
document-comparison-ai-mcp MCP server by MEOK AI Labs
Aegis Gov Contracts — last commit 2026-06-13, v1.0.0
SAM.gov federal contracts: search, details, AI bid analysis. 33k+ live opportunities.
io.github.docjet-dev/docjet-mcp — last commit 2026-06-12, v1.0.1
Render branded PDFs and PNG images from templates or raw HTML via the DocJet API. Free tier.
io.github.causa-prima-ai/scribo — last commit 2026-06-12, v1.0.0
EN 16931-compliant e-invoices: XRechnung, ZUGFeRD, Factur-X, Peppol BIS, Facturae or US PDF. Free.
com.lyrenth/lyrenth-mcp — last commit 2026-06-10, v0.1.4
Read any public web page as a clean AIDocument (Markdown + structure) through Lyrenth.
FileToPDF — last commit 2026-06-10, v0.1.1
Convert files, HTML, and Markdown to PDF via the FileToPDF API. Bring your own API key.
Epublys — last commit 2026-06-10, v1.0.1
EPUB/PDF tools: merge, split, compress, convert, edit metadata, validate ebooks.
Context Awesome — last commit 2026-06-10, v0.1.1
MCP server for accessing curated awesome list documentation
io.github.cassilup/filewash — last commit 2026-06-09, v0.1.0
Privacy-first file tools for AI agents — PDF & image ops, metadata scrubbing, background removal.
io.github.0xka13b/ms-sharepoint-mcp — last commit 2026-06-08, v1.0.1
Microsoft SharePoint MCP server — access sites, lists, and documents through Microsoft Graph.
CourtAPI — Federal Court Data — last commit 2026-06-08, v0.1.0
Search and retrieve US federal court cases, dockets, claims, and documents via PACER
io.github.gokmengokhan/endnote-mcp — last commit 2026-06-07, v1.4.8
Search, cite, and read PDFs from your EndNote library in Claude Desktop
io.github.bch1212/agentfetch — last commit 2026-06-06, v1.0.1
Token-budgeted web fetch for AI agents — auto-routes Jina, FireCrawl, Trafilatura, PDF.
io.github.bch1212/mcp-grantiq — last commit 2026-06-06, v1.0.1
Search US grants + federal contracts (Grants.gov + SAM.gov) from any LLM.
io.github.Amalgix-io/Amalgix — last commit 2026-06-01, v1.1.0
Cross-model evidence pipeline for financial filings & contracts. x402 pay-per-call.
Torify — Japan Locale APIs for AI Agents — last commit 2026-05-29, v0.2.0
39 Japanese locale APIs — wareki, NTA invoice, 法人番号, postal, romanization, kanji-kana (Workers AI).
BidSparq — last commit 2026-05-29, v0.3.4
55 tools for federal/state/local RFPs, awards, vendors, contact graph, contract vehicles, pursuits.
io.github.fieldcure/filesystem — last commit 2026-05-25, v1.1.2
Secure MCP server for sandboxed filesystem operations with document parsing support.
io.github.bperezpereira/mcp — last commit 2026-05-15, v1.0.0
Chilean DTE/SII invoicing — issue invoices, reconcile payments and manage clients with AI agents.
Kamy — last commit 2026-05-14, v1.2.0
Document API for AI-native software: render PDFs, e-sign, PAdES-seal, and verify.
com.mcparmory/alchemy-nft — last commit 2026-05-12, v1.0.3
Retrieve NFT metadata, ownership, and contract details across blockchains
com.mcparmory/convertapi — last commit 2026-05-12, v1.0.4
Convert files across 500+ formats: documents, PDFs, and images
com.mcparmory/outline — last commit 2026-05-12, v1.0.2
Create, manage, and organize team documents, collections, and share permissions
com.mcparmory/pdfco — last commit 2026-05-12, v1.0.2
Extract data, edit, convert, and parse PDF documents with OCR and AI
com.mcparmory/ragie — last commit 2026-05-12, v1.0.2
Ingest, manage, and retrieve documents for RAG-powered AI applications

Exists, but quiet (6)

No commit in the last 90 days. Often fine for something small and finished, risky for anything you need fixed.

deAPI MCP Server — last commit 2026-05-04, v0.3.0
35 AI tools for image/video generation, TTS, transcription, OCR & embeddings via deAPI
io.github.06ketan/slideshot — last commit 2026-05-03, v4.4.0
Convert HTML to PDF/PNG/WebP/PPTX slide carousels with 11 themes — for LinkedIn, decks, posts.
io.github.Combjellyshen/zotero-bridge — last commit 2026-05-02, v1.0.3
MCP Server for Zotero SQLite Database - collection, tagging, PDF reading and more.
Elasticflow — last commit 2026-05-01, v1.0.0
AI-native team workspace — tables, documents, workflow automation, live dashboards & analytics
io.github.dontsovcmc/tochka-bank — last commit 2026-04-29, v0.6.2
MCP server for Tochka Bank API — payments, invoices, acquiring, subscriptions
MoltAwards — last commit 2026-04-28, v0.2.3
Federal + state government contracts, awards, jobs, and B2B subcontracting for AI agents.

Repository gone or archived (4)

The registry still lists these, but the linked repository returns 404 or the owner archived it. Shown so you do not spend time discovering that yourself.

ai.smithery/docfork-mcp — archived by owner, last commit 2026-06-13, v0.7.0
@latest documentation and code examples to 9000+ libraries for LLMs and AI code editors in a singl…
io.github.friendlygeorge/jobber-mcp-server — archived by owner, last commit 2026-06-11, v1.0.0
MCP server for Jobber (home services SaaS) — exposes tools for clients, jobs, invoices, and quote...
io.github.friendlygeorge/stripe-mcp-server — archived by owner, last commit 2026-06-06, v1.0.0
MCP server for Stripe API — customers, charges, payments, subscriptions, products, and invoices
io.github.ayo-nci/bulkrender — archived by owner, last commit 2026-05-30, v1.1.1
Generate DOCX and PDF documents from AI assistants using BulkRender templates.

Page 4 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.