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 (48)

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

Avukatim Legal Search — v1.0.1
Search Turkish laws, court decisions, and legal documents using AI.
Agent Utility API — v1.1.0
x402 pay-per-call tools: company enrichment, PDF extraction, Amazon/KDP data, YouTube transcripts.
ContractOracle-Sentinel — v1.0.0
DeFi smart contract forensic auditor and vulnerability scanner.
Legal-Logic-Fuzzer — v1.0.0
Autonomous legal contract testing suite checking syntax anomalies.
LexGuard — v1.0.0
Contract clause parser assessing corporate legal risk exposure.
SolForge — v1.0.0
Solidity smart contract generator implementing safe coding defaults.
TOS-Slayer — v1.0.0
Terms of Service contract analyzer flagging abusive clauses.
Aegis-Privacy-MCP — v1.0.0
PII and secrets sanitization gateway with advanced OCR merging logic.
Findable MCP Server — v6.91.3
Find and summarize building documents, projects, tasks, SharePoint sync state, and red flag data.
DeepSeek PDF Reader — v5.3.0
PDF文字提取(自动OCR) · 搜索(正则+高亮) · 表格(三路径) · 预览 · 摘要 · 图片 · 单页 · OCR进度推送
io.github.ForkastPredict/forkast-mcp-docs — v1.0.0
MCP server for querying Forkast documentation
QuantumScan PQC Scanner — v1.0.4
PQC scanner for GitHub repos and smart contracts. Detects quantum-vulnerable ECDSA/RSA.
io.github.GavinLee1/mcp-fleet — v0.3.0
12 MCP tools: invoice→JSON, text→SQL, PII redaction, regex & more. Free to try, pay per call.
io.github.helloderekg/bytario — v1.0.1
40 MCP tools for image, PDF, QR, barcode, data, text, color, and render operations.
io.github.helloo1568/sheetspec — v0.1.2
Contract testing and quality gates for spreadsheets created by AI agents.
Bee by HEOSSI — v0.6.10
Bee by HEOSSI: governed multimodal intelligence - chat, code, security, research, documents, memory.
JusCABA — Justicia CABA — v0.3.1
Search Buenos Aires City courts: cases, proceedings, parties, and PDF downloads
Eleata e-Invoice Validator — v0.1.1
Validate EU e-invoices (Peppol, XRechnung, Factur-X, UBL, CII) and explain error codes.
io.github.HeyZod/fylings — v1.0.0
Search, verify & screen 1M+ African companies + their government contracts across 18 registries.
io.github.holistis/3ilm-mcp — v1.0.1
Search 1,032 verified smart contract vulnerability findings from Sherlock audits by pattern.
io.github.hrtips/cvx — v1.6.0
Create, validate, and render CV PDFs from plain YAML — fully local, no accounts.
io.github.huoshuiai42/huoshui-file-converter — v1.0.0
An MCP server that provides document format conversion
io.github.huoshuiai42/huoshui-pdf-converter — v1.0.0
An MCP server that provides PDF file conversion
io.github.huoshuiai42/huoshui-pdf-translator — v1.0.0
An MCP server that provides PDF translation service
io.github.hwang-yh-cto/space-ocr — v0.1.3
Multilingual structured OCR with verified per-character bboxes for AI agents.
Ignite UI MCP Server — v15.5.1
Unified MCP server for Ignite UI — documentation, API, and CLI scaffolding
MCP Data Converter — v1.4.3
Convert between 200+ format pairs: JSON, CSV, XML, YAML, PDF, Excel, DOCX and more.
OfficeAgent.NET — v0.2.1
Create and edit real Word documents (filesystem or SharePoint): typed change plans, tracked changes
IMAGIN.studio API Docs — v0.1.17
Semantic search over IMAGIN.studio API documentation — CDN, API, integration guides, and more.
Incwo MCP — v1.0.0
Secure MCP server for exploring incwo CRM data, documents, and email workflows.
Hong Kong CourtDB — v1.0.0
Search Hong Kong court cases and read judgment documents.
io.github.infoinlet-marketplace/mcp-jp-doc-intel — v0.1.0
Japanese document AI for agents — invoice/meishi extraction, OCR, classification (hosted API).
io.github.infoinlet-marketplace/mcp-stripe — v0.1.1
Read-only Stripe for AI agents — customers, charges, subscriptions, invoices, balance.
io.github.InnarM/blank-invoice-maker — v1.0.2
Create free invoices from your AI assistant via a pre-filled blankinvoicemaker.com link.
io.github.intenttext/intenttext-mcp — v1.0.1
Parse, validate, query, and render IntentText (.it) documents for AI agents
io.github.invapi-org/invapi-mcp — v1.0.1
Extract, create, convert & validate invoices (UBL, CII, XRechnung, ZUGFeRD, PDF, Excel)
CLIO Geojson — v2.2.3
MCP server for inspecting, validating, and summarizing GeoJSON documents (stdlib only)
CLIO Jarvis — v3.6.2
JARVIS-CD MCP with a compact user pipeline contract and explicit admin compatibility profiles
Stellaroid Earn — v1.1.0
Read-only MCP server: verify credentials and browse escrows on the Stellar testnet contract.
io.github.iseppo/e-arveldaja-mcp — v0.25.3
Estonian e-arveldaja (RIK e-Financials) accounting — invoices, bank import, reports.
DicePDF — v0.1.0
Local-first PDF tools for AI agents: merge, split, extract, render, compress. Files stay on-device.
Postgram — v0.1.3
Self-hosted memory for AI agents with hybrid search, knowledge graphs, tasks, and document sync.
iz-tolk-mcp — Tolk Compiler for TON — v1.2.1
Tolk smart contract compiler for TON — compile, check, and deploy from AI assistants
io.github.jakefleming/font-proof-mcp — v0.1.0
Create and modify Font Proof documents programmatically (PDF font proofs, live from Glyphs.app).
io.github.janF19/rejstrik-mcp — v0.9.2
Czech company registry MCP that reads filed PDF financial statements — keyless, agent-native.
io.github.javierfajardo85-rgb/aiaam — v1.0.0
MAI-1 registry: search 100+ verified AI tool contracts with live reliability scores in one call.
MCP Test Utils — v3.10.1
Desktop UI automation for AI agents: screenshots, windows, mouse, keyboard, UI Automation, OCR
DanBooks — AI Bookkeeping — v1.0.2
AI bookkeeping for small business. Create invoices, log expenses, and check P&L by voice or text.

Repository gone or archived (12)

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.

ConnectIQ MCP Server — repository gone, v1.2.0
MCP server for Garmin ConnectIQ SDK documentation and resources
io.github.dgtalquantumleap-ai/ebenova-fieldops — repository gone, v1.0.2
WhatsApp booking, staff coordination, and invoice recovery for services.
io.github.dgtalquantumleap-ai/ebenova-legal-docs — repository gone, v1.5.1
Generate 27 legal document types across 18 jurisdictions via Ebenova API.
Constat Auto — Constat amiable — repository gone, v1.0.0
Remplir un constat amiable et recevoir le PDF signé par email, directement en conversation.
ContextLayer — repository gone, v0.1.0
Intelligent context infrastructure for AI teams: knowledge graph, sessions, tasks, documents.
Faktuj MCP — repository gone, v1.2.0
Generate Polish VAT invoices (Faktura VAT) as PDF
PDFSpark MCP — repository gone, v1.2.0
Convert HTML or URLs to PDF documents powered by Playwright
io.github.egorthinks/perception — repository gone, v0.1.7
Perception for AI agents: media QC asserts, image diff, OCR tiles, video/audio analysis, PDF, 3D.
io.github.epsteinj/inkbloc — repository gone, v0.1.2
Collaborative document workspace with interactive AI blocks
Ambr — repository gone, v0.3.0
Ricardian contracts for AI agents — dual-format, SHA-256 bound, legible by construction.
io.github.Gildaraio/mcp-server — repository gone, v0.7.5
Operating contracts for AI agents. Structured instructions compiled into system prompts.
DocAuto — repository gone, v0.3.0
Model Context Protocol server for the DocAuto document-generation API.

Page 9 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.