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 maintainerβs claim only.
-
io.github.popapidev/pop-mcp
β v1.1.0
Italian e-invoicing (FatturaPA/SdI), Peppol, PDF invoice generation, and account onboarding via POP
-
π΄ Gulltoppr
β v0.1.2
Resolve any EVM contract ABI (even unverified, via decompilation), read, simulate, prepare txs.
-
Pine Labs SDK API Documentation MCP Server
β v1.2.0
List and fetch official Pine Labs SDK API documentation via MCP tools.
-
io.github.praveenc/mcp-docs-server
β v0.1.0
MCP server for searching MCP protocol documentation
-
reMarkable MCP Server (Read/Write)
β v0.2.3
Read, write, and manage your reMarkable tablet β browse, upload, create folders, move, delete, OCR
-
io.github.PromptPartner/bexio-mcp-server
β v2.5.0
Swiss accounting integration for Bexio. 314 tools: invoices, contacts, projects, account balances
-
TablaCognita
β v0.2.0
MCP-native collaborative markdown editor with real-time AI document editing
-
io.github.Ptrgit1/agent-data-api
β v1.0.1
19 pay-per-call data tools for AI agents: crypto/DeFi, web, PDF, FX, weather, DNS. x402 on Base.
-
io.github.ptrinh/final-notice
β v1.0.0
Free demand-letter PDF generator for unpaid invoices, 80+ jurisdictions, 29 languages.
-
io.github.ptyagiegnyte/egnyte-mcp-server
β v1.0.0
Official Egnyte MCP Server for AI integration with document search, analysis, and collaboration.
-
io.github.PurpleDirective/quillpdf-mcp
β v0.1.1
Local-first PDF tools (merge, split, rotate, watermark, Bates, metadata) as MCP server + CLI.
-
io.github.PyJudge/pdf4vllm
β v1.0.2
PDF reader for vision LLMs. Auto-detects text corruption and switches to image mode.
-
io.github.pythia-the-oracle/pythia-oracle-mcp
β v0.10.0
Every smart contract deserves intelligence, not just data. On-chain indicators via Chainlink.
-
Qiskit Documentation MCP Server
β v0.3.0
MCP server for querying and retrieving Qiskit documentation, guides, and API references
-
Quizlar β voice-powered AI flashcards with spaced repetition
β v1.0.0
Voice-led, FSRS-scheduled flashcards from YouTube, PDFs, web, or text. Auto-graded quizzes.
-
Agent Reality Layer
β v1.2.0
Buy timestamped web, company, commerce, social, document and decision data via x402.
-
NanoPDF
β v0.1.0
AI-powered PDF editing and generation MCP server using Gemini Pro.
-
io.github.rajat79suri/visa-info
β v1.0.2
Visa requirements, documents, and FAQs for Indian passport holders. 35 countries.
-
io.github.ramalamadingdong/first-agentic-csa
β v0.7.0
FRC documentation MCP server for WPILib, REV, CTRE, Redux, and PhotonVision.
-
SharePoint MCP Server
β v1.1.1
MCP server for Microsoft SharePoint β manage folders, documents, and metadata.
-
io.github.RayAKaan/ocular-audio-mcp
β v1.1.2
MCP server for video transcripts, screenshots, and OCR on YouTube and web videos.
-
ReportFlow
β v1.3.5
Generate PDF reports from ReportFlow templates via Claude and other AI agents.
-
io.github.RECERQA/rq-scan
β v1.2.1
MCP Server for RQ-SCAN - AI-powered document OCR and data extraction platform
-
io.github.ref-tools/ref-tools-mcp
β v3.0.1
Token efficient search for coding agents over public and private documentation.
-
Lightning Enable MCP Server
β v1.21.0
AI agent Lightning payments: invoices, wallets, L402 access, API discovery, budgets, and commerce.
-
io.github.ribhav-jain/docsonar
β v0.1.1
Local document search over your folders: hybrid keyword+semantic, fully offline, read-only
-
blueΒ·auth Document Signing
β v1.0.0
Send AI-created PDFs for signature, track signers, and return verifiable document evidence.
-
io.github.rmindgh/addsign-mcp
β v0.1.4
Send documents for e-signature, track status, remind signers, and download signed PDFs via AddSign
-
io.github.RobThePCGuy/rag-vault
β v1.5.3
Local RAG MCP server with hybrid search, PDF/DOCX support, and zero-config setup
-
Hi AI Tutor MCP
β v0.1.0
Read-only product knowledge for interactive lessons from PDFs, notes, or a topic
-
Llama AI MCP
β v0.1.0
Use Llama AI Chat to test Meta Llama 4 Maverick on code review, long PDFs, and screenshots.
-
DocVerdict
β v1.0.0
PDF, photo, email, and file comparison evidence checks with plain-language reports.
-
Fixzi β MCP & API Schema Drift Monitor
β v1.0.2
Monitor MCP servers, API contracts and AI outputs for schema drift. Alerts on breaking changes.
-
io.github.RoleModel/optics-mcp
β v0.2.6
MCP Server for Optics Design System documentation and token usage.
-
CoreWise
β v1.0.0
Extract structured insights from videos, podcasts, articles, and PDFs with multi-model AI
-
reMarkable MCP Server
β v1.0.0
Access your reMarkable tablet - read documents, browse files, extract text and OCR
-
UIZZE
β v1.1.12
STOP UI SLOP. Free UI check; unlock 800,000+ real screens, design contracts and finish gates.
-
io.github.Samuelfmedeiros/arachne-mcp
β v1.1.2
Arachne MCP β scraping, visΓ£o, OCR, RAG + VRT visual (15 tools).
-
io.github.SamuelSHernandez/laserfiche-mcp
β v2.2.0
MCP server for self-hosted Laserfiche repositories β search and read documents from Claude.
-
io.github.sathvic-kollu/techtenstein-pdf
β v1.0.2
PDF text and table extraction plus metadata. Supports OCR for scanned documents.
-
Scope (AEC) - Preview
β v0.1.1
AEC subcontractor vendor procurement plumbing layer. Preview V3 2027. Patent pending.
-
io.github.Sean-Bravo/taxformatter
β v0.1.2
Parse crypto CSVs and bank PDFs into clean transaction data for Koinly, TurboTax, CoinLedger.
-
IT Glue
β v0.4.0
IT Glue MCP server for MSPs β documents, flexible assets, semantic vector search, RBAC, and BYOK
-
io.github.sergii-ziborov/weavatrix-online
β v0.3.1
Source-free Weavatrix MCP: preview-gated sync, advisories, malware review, architecture contracts.
-
Kaseya BMS MCP
β v0.1.0
CLI and MCP server for Kaseya BMS PSA: tickets, CRM, contracts, finance, and offline analytics.
-
PandaDoc MCP
β v0.1.0
Every PandaDoc endpoint, plus an offline document pipeline no other PandaDoc tool has - stalled
-
Nova Scotia Data Explorer
β v1.0.0
Query and explore Nova Scotia open datasets via the Socrata SODA API.
-
Native DevTools
β v0.10.1
MCP server for desktop, browser (CDP), and Android automation. Screenshot, OCR, click, type.
-
shuck-convert
β v1.0.0
Convert between document formats β DOCX/PDF to Markdown, Markdown to DOCX.
-
io.github.shigetosidumeda-cyber/autonomath-mcp
β v0.5.0
Japanese public-program MCP β subsidies, loans, tax, law, invoice. 261 tools, Β₯3/billable unit
-
io.github.Shreyas-Profile/docs-mcp
β v0.1.0
Vector RAG store for Word/Excel/PDF/PowerPoint. Break-even pricing, $5 per 5,700 pages.
-
io.github.Shuangshuang007/workopia
β v1.0.1
Workopia - free MCP for global job search, PDF resume builder, and AI career advice.
-
io.github.siriuslattice/evmcp
β v0.1.3
Multi-chain EVM blockchain data with companion smart contracts
-
io.github.skypier-jp-works/mcp-jp-corporate-id
β v1.0.0
Validates and normalizes Japanese corporate numbers and invoice registration numbers (format only).
-
Stratum MCP
β v0.2.42
Structured execution for Claude Code β contracts, postconditions, gates, guardrails.
-
io.github.smartpolicy-protocol/smartpolicy
β v0.2.0
Runtime authorization for AI agents and smart contracts via an immutable on-chain policy registry
-
io.github.smythmyke/govtoolspro-mcp-server
β v0.1.3
Workflow tools for federal contractors: go/no-go scoring, incumbent intel, recompete, NECO.
-
FreelanceOS
β v0.2.2
Freelance business manager β clients, proposals, invoices, time tracking, scope, and follow-ups.
-
Santuri
β v1.1.7
Search official documentation for well-known libraries.
-
doiget
β v0.8.6
OA-first paper fetcher: DOIs/arXiv IDs to local PDFs + metadata via Open Access APIs.
Page 14 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.