ZBS Index What actually exists in applied AI, with the source next to it

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 (60)

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

  • com.sendpageapp/sendpage — last commit 2026-08-02, v1.0.0
    Publish an HTML document as a link anyone can open in one tap, plus PDF, image and Word export.
  • io.github.eltociear/contract-guard-mcp — last commit 2026-08-02, v1.1.0
    EVM contract/token risk check + ERC20 approval (proxy, EIP-7702, unlimited-allowance). Zero deps.
  • io.github.Doucs91/hivelore — last commit 2026-08-02, v0.53.1
    Deterministic gate: blocks any commit whose diff reintroduces a documented team mistake.
  • ai.thrain/blackout — last commit 2026-08-02, v1.3.0
    Permanent local PDF redaction: text is removed and verified gone, not covered. No uploads.
  • Receipt Extraction — last commit 2026-08-02, v0.1.2
    AU GST/ABN receipt extraction — assigns entertainment/ITC tax codes per line, not just OCR.
  • agentverse — last commit 2026-08-01, v1.0.1781779784
    MCP server for agentverse documentation, generated by doc2mcp.
  • cavalry — last commit 2026-08-01, v1.0.1781655028
    MCP server for cavalry documentation, generated by doc2mcp.
  • developer — last commit 2026-08-01, v1.0.1782461537
    MCP server for developer documentation, generated by doc2mcp.
  • innovationlab — last commit 2026-08-01, v1.0.1780737423
    MCP server for innovationlab documentation, generated by doc2mcp.
  • langchain — last commit 2026-08-01, v1.0.1781396655
    MCP server for langchain documentation, generated by doc2mcp.
  • lightfield — last commit 2026-08-01, v1.0.1780875164
    MCP server for lightfield documentation, generated by doc2mcp.
  • manus — last commit 2026-08-01, v1.0.1780872068
    MCP server for manus documentation, generated by doc2mcp.
  • opencode — last commit 2026-08-01, v1.0.1782367812
    MCP server for opencode documentation, generated by doc2mcp.
  • stocksense-ai — last commit 2026-08-01, v1.0.1783197997
    MCP server for stocksense-ai documentation, generated by doc2mcp.
  • sunpeak — last commit 2026-08-01, v1.0.1780873603
    MCP server for sunpeak documentation, generated by doc2mcp.
  • tabletopsimulator — last commit 2026-08-01, v1.0.1781925825
    MCP server for tabletopsimulator documentation, generated by doc2mcp.
  • uagents — last commit 2026-08-01, v1.0.1781555819
    MCP server for uagents documentation, generated by doc2mcp.
  • io.github.CSOAI-ORG/contract-review-ai-mcp — last commit 2026-08-01, v1.0.10
    Contract Review Ai MCP Server by MEOK AI Labs
  • io.github.CSOAI-ORG/agent-prompt-injection-firewall-mcp — last commit 2026-08-01, v1.0.13
    The WAF for agents. Pattern-based + heuristic firewall scans prompts, RAG documents, tool argume...
  • com.auto-reader/ocr — last commit 2026-08-01, v1.0.3
    Arabic-first OCR, translation and document extraction. First call mints a free trial key.
  • MCP Market Russia — last commit 2026-08-01, v3.2.0
    Russian construction market: 3,395 contractors, 20,322 projects, 24 search/analytics tools.
  • io.github.AINative-Studio/ainative-prd-mcp — last commit 2026-08-01, v1.1.1
    PRD Generator MCP — generate, validate, and manage Product Requirement Documents.
  • Vitex — AI Resume Generator — last commit 2026-08-01, v0.2.1
    Generate tailored, ATS-optimized resume PDFs and cover letters from a job description, over MCP.
  • Gemina FileTag — last commit 2026-07-31, v1.0.2
    Tag, rename, and enrich PDFs and images. Free tier: 1,500 tags/month, no credit card.
  • io.github.groupdocs-comparison/groupdocs-comparison-mcp — last commit 2026-07-31, v26.7.5
    MCP server for GroupDocs.Comparison — compare, analyze, and inspect documents via AI agents.
  • Docling MCP — last commit 2026-07-31, v3.0.0
    Convert PDFs and other documents to structured formats via Docling, for AI applications.
  • io.github.barateza/mcp-plesk-dev-docs — last commit 2026-07-30, v0.6.0
    An MCP server that indexes and retrieves Plesk documentation.
  • Scope (AEC) - Preview — last commit 2026-07-30, v1.0.9
    AEC subcontractor vendor procurement plumbing layer. Preview - V3 launches 2027.
  • io.github.cyanheads/socrata-mcp-server — last commit 2026-07-30, v0.1.14
    Search and query government open-data portals (Socrata SODA API).
  • io.github.cyanheads/libofcongress-mcp-server — last commit 2026-07-30, v0.2.16
    Search LOC digital collections, Chronicling America newspapers (full OCR), and LC Subject Headings.
  • io.github.cyanheads/docgen-mcp-server — last commit 2026-07-30, v0.2.1
    Render HTML/markdown to PDF, export rows to xlsx, and fill AcroForm PDFs.
  • io.github.ACTA-Team/docs-mcp — last commit 2026-07-30, v0.1.3
    Read-only MCP server for the official ACTA verifiable credentials documentation.
  • io.github.beepboop2025/pdf-suite-mcp — last commit 2026-07-30, v2.1.2
    37 tools to read, create, merge, split, watermark, fill, redact & search PDFs. Local, no API key.
  • io.github.beepboop2025/pdf-toolkit-mcp — last commit 2026-07-30, v2.1.1
    37 tools to read, create, merge, split, watermark, fill, redact & search PDFs. Local, no API key.
  • Stellar Agent Search — last commit 2026-07-30, v0.1.0
    Discover and rank Stellar 8004 agents with a read-only MCP server and fail-closed contract probes.
  • Avalara Developer Documentation — last commit 2026-07-30, v1.0.1
    Provides access to Avalara developer documentation, integration guides, and code examples
  • Avalara E-Invoicing & Live Reporting — last commit 2026-07-30, v1.0.0
    Provides access to Avalara E-Invoicing and Live Reporting APIs for document statuses and compliance
  • com.apple-rag/mcp-server — last commit 2026-07-30, v2.9.0
    Apple Developer Documentation with Semantic Search, RAG, and AI reranking for MCP clients
  • io.github.CryptoAPIs-io/mcp-contracts — last commit 2026-07-30, v0.3.0
    MCP server for smart contract ABIs and on-chain data from EVM and Solana via Crypto APIs
  • OpenArx — last commit 2026-07-30, v0.3.2
    Open scientific and engineering knowledge for AI agents: search, evidence, document publishing.
  • Pdfrender — last commit 2026-07-29, v1.0.0
    HTML-to-PDF MCP server — render pixel-faithful PDFs from HTML.
  • KDAN PDF — last commit 2026-07-29, v1.0.0
    Upload, edit, compress, protect, redact, and compare PDFs with KDAN PDF in Claude and ChatGPT.
  • Laddro Career — last commit 2026-07-28, v0.4.0
    Tailor resumes, generate cover letters, render CVs as PDF, and browse 22+ templates.
  • ca.swiftsign/mcp — last commit 2026-07-28, v0.5.2
    E-signatures for agents: mint a sandbox key, send PDFs, track status, download the sealed result.
  • Final POS Docs — last commit 2026-07-28, v1.0.0
    Search the Final POS REST API documentation.
  • io.github.Achilles1089/pentagonal-mcp — last commit 2026-07-27, v1.0.1
    AI smart contract forge — 8-agent security audits, generation, and compilation across 8 chains
  • Stellary Project Management MCP Server — last commit 2026-07-27, v0.12.0
    Connect AI assistants to Stellary projects, boards, documents, and governed agent workflows.
  • io.github.bitterdev/pdf-letter-mcp — last commit 2026-07-27, v1.0.3
    Renders letters as print ready PDFs, DIN 5008 compliant for German window envelopes.
  • io.gildara/mcp-server — last commit 2026-07-27, v0.8.0
    Operating contracts for AI agents. Structured instructions compiled into system prompts.
  • io.github.CSOAI-ORG/pdf-tools-ai-mcp — last commit 2026-07-26, v1.0.4
    pdf-tools-ai-mcp MCP server by MEOK AI Labs
  • MCP Office Word — last commit 2026-07-26, v0.7.0
    50-tool Word MCP server. Document assembly, tracked changes, and export. Windows-first.
  • QuickBooks Online MCP Server — last commit 2026-07-26, v0.1.0
    QuickBooks Online MCP server for invoices, customers, and payments. OAuth 2.1 + PKCE, stdio/HTTP.
  • Hashloom — last commit 2026-07-26, v0.5.0
    Content-addressed contracts and a verification cache that cut agent context by skipping proven code.
  • Heddle — last commit 2026-07-26, v0.3.3
    Content-addressed contracts and a verification cache that cut agent context by skipping proven code.
  • au.com.ato-mcp/ato-mcp — last commit 2026-07-26, v2.1.5
    Australian tax knowledge base for agents: 34,500+ ATO documents, cited answers to any tax question.
  • io.github.groupdocs-total/groupdocs-total-mcp — last commit 2026-07-25, v26.7.3
    MCP server for GroupDocs.Total — annotate, sign, convert, watermark, parse, redact documents via AI.
  • io.github.groupdocs-metadata/groupdocs-metadata-mcp — last commit 2026-07-25, v26.7.3
    MCP server for GroupDocs.Metadata — read, search, write, and remove document metadata.
  • io.github.groupdocs-annotation/groupdocs-annotation-mcp — last commit 2026-07-25, v26.7.4
    MCP server for GroupDocs.Annotation — add, list, update, remove document annotations via AI agents.
  • io.github.groupdocs-signature/groupdocs-signature-mcp — last commit 2026-07-25, v26.7.2
    MCP server for GroupDocs.Signature — sign, search and verify document signatures via AI agents.
  • io.github.groupdocs-markdown/groupdocs-markdown-mcp — last commit 2026-07-25, v26.7.2
    MCP server for GroupDocs.Markdown — convert documents to Markdown via AI agents.

Page 2 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.