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.

TheCrawler — v0.5.8
Universal web scraper with LLM-ready markdown, RAG chunking, PDF/DOCX support.
mdedit.ai — v0.2.1
Create, read, edit, review, and explicitly publish Markdown Documents in mdedit.ai.
io.github.mapbox/mcp-devkit-server — v0.8.2
Provides AI assistants with direct access to Mapbox developer APIs and documentation.
io.github.marras0914/agent-toolbelt-mcp — v1.0.0
19 focused API tools for AI agents: contract review, prompt optimizer, context packing, and more.
Government Contracts — v1.0.0
SAM.gov contracts and USAspending awards. 4 procurement tools.
io.github.MarvinRey7879/framefetch — v1.9.1
Any social-video URL → transcript, metadata, frames, OCR, summary, search, Q&A. MCP server + x402.
Mastercard Developers MCP — v0.1.0
Access Mastercard Developers APIs, documentation, and API specifications through MCP.
io.github.mastrophot/contract-security-scanner — v0.1.1
MCP smart contract scanner with NEAR-focused security context.
io.github.matematicsolutions/de-eli-mcp — v0.4.3
German law MCP: legislation (NeuRIS), case law (RII, Open Legal Data), Bundestag DIP documents.
HomeClip Trust Layer — v1.0.0
Find and verify trustworthy US home-services contractors by their un-buyable HomeClip Trust Score.
Nota Fiscal — v0.1.0
Issue and manage Brazilian service invoices (NFS-e) by chatting with your agent, platform-hosted, no
NotebookLM — v0.1.0
Google NotebookLM via natural language: create notebooks, add sources (PDF, URL, YouTube) and ask gr
Social → Context — v0.1.0
Turn a TikTok/Instagram/YouTube link into text for your AI: metadata, transcript and image OCR.
PDF Generator — v2.0.6
MCP server for creative PDF generation with full emoji, Unicode, and offline support
io.github.MCPServings/paper-mcp — v0.5.0
Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.
io.github.mdfifty50-boop/docx-forge — v0.1.1
Professional document generation from structured data
io.github.MDMagic-MCP/mdmagic-mcp-server — v1.7.14
Use your own Word templates to convert Markdown → DOCX/PDF/HTML from any MCP-compatible AI.
JAIL Search — v1.4.0
Search a billion+ documents — papers, books, code, legal cases, forums, Wikipedia, and more.
io.github.mehtaphysical13/pdf-tables-mcp — v0.1.0
Reliable PDF table extraction. Pass a URL, get structured JSON tables with citations.
io.github.Melusi-M/fixmypdf — v1.0.0
Privacy-first PDF tools over MCP: merge, split, rotate, delete, compress, protect, inspect.
PLwC - Personality Layer with Conscience — v0.2.0-rc18.dev9
Governed local MCP gateway for workspace, sandbox, document and profile operations.
Clutter — v0.1.4
Generate synthetic companies, documents & data via the Clutter API (e.g. to fill SharePoint).
io.github.michu5696/agora402 — v0.5.3
Escrow protection for agent payments on Base — USDC held in smart contract until job completion.
io.github.michu5696/paycrow — v1.0.0
Escrow protection for agent payments on Base — USDC held in smart contract until job completion.
io.github.mifactory-bot/mifactory-contratos — v1.2.0
Freelance contracts via API for any country. AI-generated or PDF. Pay-per-use: $5-$20.
io.github.mifactory-bot/mifactory-pdf — v1.0.0
Send transactional pdfs for AI agents via SMTP. Templates included.
io.github.MikeAshtonEILLC/usdi-mcp-server — v1.0.0
Live tools for USDi: CPI-indexed exchange rate, contract/pool addresses, and mint/redeem mechanics.
Mila — v1.0.2
Create and manage documents, spreadsheets, and presentations from your AI assistant.
Daily Data Feeds — v1.0.0
Daily data: jobs, VC funding, domain drops, patents, gov contracts, crypto. Bitcoin pay-per-month.
Microsoft Office — v0.2.0
Microsoft Office MCP server: read and edit Word documents, Excel workbooks, and PowerPoint files
PandaDoc — v0.2.2
PandaDoc document automation MCP server for Model Context Protocol hosts
QuickBooks Online — v0.3.1
QuickBooks Online MCP server: invoices, bills, customers, vendors, employees, and accounts
AskAIs AI Receipt Generator — v1.0.1
Generate professional receipt PDFs and structured receipt data with AI-ready MCP tools.
io.github.Mintii-Labs/ozor — v2.0.1
Generate AI videos from a prompt or document (PDF/PPTX/DOCX/URL) and export shareable MP4s.
io.github.mintmas/oracle42-intelligence — v1.0.0
AI-powered threat intelligence, smart contract auditing, and cybersecurity OSINT.
Toolora MCP Server — v1.0.0
12 free tools: PDF, OCR, QR codes, audio transcription, URL scraping, Excel, Word. No key needed.
NodeRooms Discovery — v1.0.0
Read-only NodeRooms Agent discovery, safety policy, public indexes, and arrival contract.
io.github.mlintangmz2765/scholar — v1.0.0
Hardened Scholar MCP for deep academic research (Scopus, OpenAlex, Unpaywall) with PDF vision.
PDF Modifier — v1.6.0
Modify PDF text, replace with regex, and analyze layout while preserving fonts.
io.github.MLTCorp/convertfilefast — v0.1.4
Convert files, run PDF/image tools, create billing links, and report feedback.
io.github.MohibShaikh/hwcontract — v0.1.1
Judge hardware timing/serial against a contract: pass/marginal/fail (WS2812, DShot, logs)
JustFill PDF Form Automation — v0.4.7
Fill existing fillable, flat and scanned PDF forms from structured data; save reusable templates
io.github.mrslbt/pdf-it — v2.1.0
Native PDF renderer for AI markdown. Cover, TOC, page-numbered footer. Fonts embedded, zero config.
OmniClip RAG — v0.4.8
Read-only local-first MCP server for private Markdown, PDF, and Tika-backed search on Windows.
IT Glue — v0.4.1
IT Glue MCP server for MSPs — documents, flexible assets, semantic vector search, RBAC, and BYOK
io.github.MusaddiqueHussainLabs/mhlabs_mcp_tools — v3.0.0
An MCP server that provides text preprocessing, NLP components, and document analysis
io.github.MUSE-CODE-SPACE/vibe-coding — v2.12.1
Auto-document vibe coding sessions - collect, summarize, and publish
Frappe MCP Server — v1.2.0
Interact with Frappe/ERPNext sites — document CRUD, search, and whitelisted method calls
io.github.mutonby/aikount-mcp — v0.1.1
Contabilidad española con IA: facturas, gastos por OCR, conciliación bancaria y Modelo 303.
pdfmux — v1.8.7
PDF-to-Markdown extraction that audits its own output and flags any extractor's silent drops.
PinRAG — v0.9.27
MCP RAG: index PDFs, repos, YouTube, Discord, text; optional YouTube vision; query with citations.
io.github.NeerajG03/vector-memory — v0.4.4
Semantic document memory using Redis vector store. Save and recall files with natural language.
io.github.neuledge/context — v0.2.3
Local-first documentation for AI agents. Offline, instant, private doc retrieval.
Maket — v1.4.4
Compose branded visual documents with live preview, data collections, validation, and PDF export.
Gnosis MCP — v0.13.3
Zero-config MCP server for searchable documentation. SQLite or PostgreSQL.
Doc_Conv — Document to Markdown — v1.0.1
Convert PDF/Word/Excel/PowerPoint documents to Markdown, paid in USDC via x402.
io.github.NicolasMartalog/docweave-mcp — v0.2.0
Generate and read PDFs for AI agents: a generate_pdf and a read_pdf tool, priced per document.
Sentor — v1.0.5
Score sentiment toward specific entities in text. Cluster documents and name topics.
io.github.nimish14/freelance-ops-mcp — v0.1.0
Freelance invoice ops MCP — overdue status, tone suggestion, and reminder drafts
dokumendiregister.ee — Estonian public-authority documents — v1.0.0
Estonian public-authority document registers: one search across all, docs linked to companies.

Page 11 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.