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.

• io.github.speakmancip/speakmanai — v1.0.10
  Multi-agent AI pipeline that generates professional Solution Architecture Documents.
• Boltwork — v0.1.12
  AI services via Bitcoin Lightning — PDF summarisation, code review, translation and more.
• Strutter AI — v1.0.0
  AI-powered RFP response management. Search Q&A libraries, draft responses, and upload documents.
• io.github.sudohnim/eidolon — v0.1.0
  Privacy-first OSINT scanner: breaches, credentials, Shodan, username sweep. Scored PDF report.
• AILANG Parse — v0.8.0
  Deterministic DOCX/PPTX/XLSX/PDF parser: track changes, comments, headers, footers, merged cells.
• Suparse Document Processing — v1.3.0
  Extract structured data from PDFs and documents with Suparse AI OCR.
• Evocrawl MCP Server — v4.0.1
  MCP server for Evocrawl — search, scrape, and interact with the web.
• Word Document Operations — v1.0.0
  Read, create, and modify Microsoft Word documents
• io.github.sweetcucumbersalad/differino-mcp — v0.5.1
  Compare PDF, DOCX, and TXT documents from any AI agent: diff, change summary, and PDF export.
• io.github.Swih/mistral-mcp — v0.8.2
  Mistral AI MCP server: chat, OCR, Voxtral audio, Codestral FIM, vision, agents, batch.
• io.github.syedtaj7/kitbag-mcp — v1.1.2
  Zero-config MCP server bundling 50+ utility tools: converters, OCR, scraping, and formatters.
• Image Reader MCP — v0.1.0
  Evidence-first image MCP. Agent Media Twin with metadata and citeable OCR evidence.
• PDF Reader MCP — v4.1.2
  Evidence-first PDF MCP. Agent Document Twin with citeable page+bbox evidence.
• Video Reader MCP — v0.1.0
  Evidence-first video MCP. Timeline document with ffprobe streams and subtitle cues.
• Talonic — v0.1.73
  Extract structured, schema-validated data from PDFs, scans, images, spreadsheets, and forms.
• io.github.tamas-fm/project-lore — v0.1.1
  A local-first MCP server that routes development tasks to authoritative project documentation.
• Stashot — v0.8.0
  Capture, OCR-search, and retrieve local Mac screenshots for AI agents through Stashot.
• io.github.taytrom/bitsbound-contract-automation — v1.0.14
  AI contract automation with partner-level redlines, OOXML Track Changes, and risk analysis.
• AppHandoff MCP Server — v1.0.1
  Shared live context for AI agents and humans — API specs, DB schemas, and contract mismatches.
• io.github.TemplateFoxPDF/mcp-server — v1.9.7
  MCP server for TemplateFox PDF generation API - Generate PDFs from templates via AI assistants
• SENTINEL — v1.0.1
  Pre-execution safety oracle for AI agents. Screens Base contracts, simulates sells, pays via x402.
• FundingLandscape — v2.1.1
  Search 21,000+ open US grants, SAM.gov contracts, and foundations. Checked daily, free tier.
• io.github.themoddedcube/pdf-report-generator — v1.0.1
  Generate professional PDF reports from LLM output — cover, TOC, tables, charts, 5 themes.
• io.github.therealMrFunGuy/invoice-pilot — v1.0.0
  PDF invoicing with auto-chase reminders, email delivery, and payment tracking.
• PDFTools — v1.0.0
  Extract text and tables from PDFs, merge documents, and get metadata.
• io.github.therealMrFunGuy/screenshot-api — v1.0.0
  Website screenshots as PNG, JPEG, or PDF with custom viewports and full-page capture.
• 1c-rest-mcp — v1.2.1
  MCP server for 1C Enterprise — ERP catalogs, documents via REST API (Russia)
• io.github.theYahia/amocrm-mcp — v1.0.1
  MCP server for amoCRM API — leads, contacts, pipelines. Auth: Bearer token.
• io.github.theYahia/robokassa-mcp — v1.0.0
  MCP server for Robokassa payment API — generate payment URLs, check invoice status. First MCP for R
• io.github.Thourum/billy-mcp — v0.3.2
  Billy (billy.dk) accounting: invoices, journal entries, trial balance, with write protection.
• io.github.timescale/pg-aiguide — v0.5.1
  Comprehensive PostgreSQL documentation and best practices, including ecosystem tools
• Tiger MCP — v0.21.2
  Provides programmatic access to Tiger Cloud services, databases, and documentation.
• io.github.Timwal78/402proof — v1.0.0
  x402 payment firewall + Agent Credit Bureau. Invoice/verify/score via RLUSD on XRPL.
• mcp-x402 — MCP server for agents with autonomous USDC/RLUSD payments — v2.3.0
  85+ pay-per-call MCP tools: trading, federal grants/contracts, SEC, FTD. x402 USDC/RLUSD. No keys.
• io.github.tradewr333-lgtm/axp — v0.1.1
  Trust scores, opportunity feed, contracts and a paid crypto Decision API for AI agents.
• Transloadit Media Processing — v0.3.9
  Process video, audio, images, and documents with 86+ cloud media processing robots.
• Teneo Book Generation — v1.0.1
  Generate complete nonfiction books with Teneo: outline, manuscript, cover, and PDF/EPUB/DOCX files.
• melta UI — v1.3.0
  AI-Ready design system MCP: melta UI tokens, component contracts, 99 rules, check_html self-verify
• io.github.uditk2/review-assist-mcp — v0.3.1
  Turns an AI coding agent session into a reviewable Intent Document, validated against the diff.
• io.github.UI5/webcomponents-react-mcp-server — v2.25.0
  MCP server for UI5 Web Components for React - Developer documentation and API assistance
• Unmarkdown — v1.0.3
  The document publishing layer for AI tools. Convert markdown to 6 destinations, 62 templates.
• io.github.us-all/openmetadata — v1.16.10
  OpenMetadata MCP — metadata, lineage, search, data quality, OM 1.12+ Data Contracts
• Safe Docx — v0.19.1
  AI-native surgical editing of Word .docx and OpenDocument .odt files with formatting preservation
• io.github.User0856/snaprender — v1.5.4
  Screenshot, extract content, and render web pages. PNG/JPEG/WebP/PDF, batch, signed URLs.
• io.github.varaprasadreddy9676/huly-mcp — v0.5.4
  MCP server for Huly — manage projects, issues, documents and more via natural language.
• Htmlpdf Transform Mcp — v1.0.0
  Htmlpdf Transform Mcp connects AI agents to real public APIs via MCP. Tools include
• io.github.vaughnyb/ai-screening — v1.0.1
  AI hiring tools CV screening, social media profile scan, and document search for any organization.
• PageIndex MCP — v1.8.2
  Reasoning-based RAG system for chatting with long PDFs. Supports local and online files.
• io.github.Vektoris-AI/proofetch — v0.0.2
  Verified extraction: source-backed JSON from PDFs/URLs; honest null + signed receipt.
• PDF Card MCP — v0.1.2
  Local-first MCP server + CLI that turns PDFs into source-linked, card-based HTML readers.
• io.github.VictoriaMetrics-Community/mcp-victorialogs — v1.8.0
  MCP Server for VictoriaLogs. Provides integration with VictoriaLogs API and documentation
• io.github.VictoriaMetrics-Community/mcp-victoriametrics — v1.18.0
  MCP Server for VictoriaMetrics. Provides integration with VictoriaMetrics API and documentation
• io.github.VictoriaMetrics-Community/mcp-victoriatraces — v1.5.0
  MCP Server for VictoriaTraces. Provides integration with VictoriaTraces API and documentation
• io.github.VictoriaMetrics/mcp-victorialogs — v1.9.0
  MCP Server for VictoriaLogs. Provides integration with VictoriaLogs API and documentation
• io.github.VictoriaMetrics/mcp-victoriametrics — v1.120.1
  MCP Server for VictoriaMetrics. Provides integration with VictoriaMetrics API and documentation
• AndroJack MCP — v2.0.0
  Android engineering MCP server with verified documentation grounding and AI validation tools.
• htmldrop — v0.1.0
  Publish HTML, Markdown, PDF, or images as instant shareable links with expiry and passwords.
• PDF Triage — v0.1.2
  Read local PDFs without uploading. Classifies first, flags untrustworthy text, bounds output.
• io.github.visus-mcp/visus-mcp — v0.13.0
  Security-first web access. Sanitizes pages, blocks injection, redacts PII. Now with PDF/JSON/SVG.
• AbraFlexi — v1.0.1
  MCP server for AbraFlexi ERP — invoices, contacts, products, bank transactions.

Page 15 of 17

• ← Previous
• Page 1
• Page 13
• Page 14
• Page 15 (you are here)
• Page 16
• Page 17
• Next →

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.